diff --git a/runs/frontier-fidelity-envelope-v1/.gitignore b/runs/frontier-fidelity-envelope-v1/.gitignore index 008f888..29cb6f8 100644 --- a/runs/frontier-fidelity-envelope-v1/.gitignore +++ b/runs/frontier-fidelity-envelope-v1/.gitignore @@ -6,3 +6,4 @@ simulator-a2/ simulator-a3/ fleet-state/ fleet-artifacts/ +profiles/profile-v3-batch/ diff --git a/runs/frontier-fidelity-envelope-v1/prepare_exact_trace.py b/runs/frontier-fidelity-envelope-v1/prepare_exact_trace.py new file mode 100644 index 0000000..405376c --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/prepare_exact_trace.py @@ -0,0 +1,302 @@ +#!/usr/bin/env python3 +"""Prepare exact Qwen trace replays with block-16 prefix identities. + +Prompt text is written only below ``private/``. Public manifests and Frontier +fixtures contain lengths, arrivals, session IDs, and deterministic block IDs. +""" + +from __future__ import annotations + +import argparse +import csv +import hashlib +import json +import math +import platform +import socket +import time +from pathlib import Path +from typing import Any + + +CSV_FIELDS = ( + "arrived_at", + "num_prefill_tokens", + "num_decode_tokens", + "session_id", + "block_hash_ids", +) + + +def sha256(path: Path) -> str: + digest = hashlib.sha256() + with path.open("rb") as source: + for chunk in iter(lambda: source.read(1 << 20), b""): + digest.update(chunk) + return digest.hexdigest() + + +def threshold_name(value: float) -> str: + return f"u{value:.12g}".replace(".", "p") + + +def token_payload(tokens: list[int]) -> bytes: + return len(tokens).to_bytes(2, "little") + b"".join( + int(token).to_bytes(4, "little", signed=False) for token in tokens + ) + + +def block_identity_records( + token_ids: list[int], block_size: int +) -> list[tuple[int, bytes]]: + """Return parent-sensitive identities and independent collision witnesses.""" + parent = b"FRONTIER_EXACT_TRACE_ROOT" + records = [] + for start in range(0, len(token_ids), block_size): + payload = token_payload(token_ids[start : start + block_size]) + identity_input = parent + b"\0" + payload + parent = hashlib.blake2b(identity_input, digest_size=16).digest() + records.append( + ( + int.from_bytes(parent, "big", signed=False), + hashlib.sha256(identity_input).digest(), + ) + ) + return records + + +def block_identities(token_ids: list[int], block_size: int) -> list[int]: + """Return parent-sensitive identities with the same prefix equivalence as vLLM.""" + return [identity for identity, _ in block_identity_records(token_ids, block_size)] + + +def root_sessions(rows: list[dict[str, Any]]) -> dict[int, int]: + roots: dict[int, int] = {} + for row in rows: + chat_id = int(row["chat_id"]) + parent = int(row["parent_chat_id"]) + roots[chat_id] = chat_id if parent == -1 else roots.get(parent, parent) + return roots + + +def update_digest(digest: Any, values: list[Any]) -> None: + digest.update(json.dumps(values, separators=(",", ":")).encode()) + digest.update(b"\n") + + +def parse_args() -> argparse.Namespace: + parser = argparse.ArgumentParser() + parser.add_argument("--trace", type=Path, required=True) + parser.add_argument("--model", type=Path, required=True) + parser.add_argument("--output-root", type=Path, required=True) + parser.add_argument("--served-model-name", default="qwen3-30b-a3b") + parser.add_argument("--sampling-u-max", type=float, action="append", required=True) + parser.add_argument("--max-model-len", type=int, default=40960) + parser.add_argument("--source-block-size", type=int, default=64) + parser.add_argument("--runtime-block-size", type=int, default=16) + parser.add_argument("--batch-size", type=int, default=16) + return parser.parse_args() + + +def main() -> None: + args = parse_args() + thresholds = sorted(set(args.sampling_u_max)) + if not thresholds or thresholds[0] < 0 or thresholds[-1] > 1: + raise ValueError("sampling thresholds must be in [0, 1]") + if args.source_block_size % args.runtime_block_size: + raise ValueError("source block size must be divisible by runtime block size") + if min(args.max_model_len, args.source_block_size, args.runtime_block_size, args.batch_size) <= 0: + raise ValueError("length and batch arguments must be positive") + + import transformers + from transformers import AutoTokenizer + + rows = [json.loads(line) for line in args.trace.open() if line.strip()] + roots = root_sessions(rows) + eligible = [ + (index, row) + for index, row in enumerate(rows) + if int(row["input_length"]) + int(row["output_length"]) <= args.max_model_len + and int(row["output_length"]) > 0 + ] + tokenizer = AutoTokenizer.from_pretrained(args.model, trust_remote_code=True) + prepared: list[dict[str, Any]] = [] + identity_to_digest: dict[int, bytes] = {} + source_to_runtime: dict[int, tuple[int, ...]] = {} + runtime_to_source: dict[tuple[int, ...], int] = {} + identity_collision_count = 0 + source_to_runtime_conflicts = 0 + runtime_to_source_conflicts = 0 + length_mismatches = 0 + source_hash_count_mismatches = 0 + started = time.time() + + for start in range(0, len(eligible), args.batch_size): + batch = eligible[start : start + args.batch_size] + encoded = tokenizer( + [row["prompt"] for _, row in batch], + add_special_tokens=False, + padding=False, + truncation=False, + )["input_ids"] + for (source_index, row), token_ids in zip(batch, encoded, strict=True): + token_ids = [int(token) for token in token_ids] + if len(token_ids) != int(row["input_length"]): + length_mismatches += 1 + source_hashes = [int(value) for value in row["hash_ids"]] + if len(source_hashes) != math.ceil(len(token_ids) / args.source_block_size): + source_hash_count_mismatches += 1 + identity_records = block_identity_records(token_ids, args.runtime_block_size) + runtime_ids = [identity for identity, _ in identity_records] + for runtime_id, witness in identity_records: + previous = identity_to_digest.setdefault(runtime_id, witness) + identity_collision_count += int(previous != witness) + + blocks_per_source = args.source_block_size // args.runtime_block_size + for block_index, source_id in enumerate(source_hashes): + begin = block_index * blocks_per_source + relation = tuple(runtime_ids[begin : begin + blocks_per_source]) + previous_relation = source_to_runtime.setdefault(source_id, relation) + source_to_runtime_conflicts += int(previous_relation != relation) + previous_source = runtime_to_source.setdefault(relation, source_id) + runtime_to_source_conflicts += int(previous_source != source_id) + + prepared.append( + { + "source_index": source_index, + "chat_id": int(row["chat_id"]), + "session_id": roots[int(row["chat_id"])], + "arrival": float(row["timestamp"]), + "input_length": int(row["input_length"]), + "output_length": int(row["output_length"]), + "sampling_u": float(row["sampling_u"]), + "prompt": row["prompt"], + "runtime_block_ids": runtime_ids, + } + ) + + args.output_root.mkdir(parents=True, exist_ok=True) + threshold_manifests = [] + for threshold in thresholds: + name = threshold_name(threshold) + public = args.output_root / "public" / name + private = args.output_root / "private" / name + public.mkdir(parents=True, exist_ok=True) + private.mkdir(parents=True, exist_ok=True) + selected = [row for row in prepared if row["sampling_u"] <= threshold] + frontier_path = public / "frontier.csv" + real_path = private / "real_requests.jsonl" + vector_digest = hashlib.sha256() + with frontier_path.open("w", newline="") as output: + writer = csv.DictWriter(output, fieldnames=CSV_FIELDS, lineterminator="\n") + writer.writeheader() + for row in selected: + writer.writerow( + { + "arrived_at": f"{row['arrival']:.12f}", + "num_prefill_tokens": row["input_length"], + "num_decode_tokens": row["output_length"], + "session_id": row["session_id"], + "block_hash_ids": "|".join( + str(value) for value in row["runtime_block_ids"] + ), + } + ) + update_digest( + vector_digest, + [ + row["source_index"], + row["arrival"], + row["input_length"], + row["output_length"], + row["session_id"], + row["runtime_block_ids"], + ], + ) + with real_path.open("w") as output: + for row in selected: + output.write( + json.dumps( + { + "source_index": row["source_index"], + "arrived_at": row["arrival"], + "input_length": row["input_length"], + "output_length": row["output_length"], + "session_id": row["session_id"], + "runtime_block_ids": row["runtime_block_ids"], + "body": { + "model": args.served_model_name, + "prompt": row["prompt"], + "min_tokens": row["output_length"], + "max_tokens": row["output_length"], + "ignore_eos": True, + "stream": True, + }, + }, + separators=(",", ":"), + ) + + "\n" + ) + threshold_manifests.append( + { + "sampling_u_max": threshold, + "selected_requests": len(selected), + "request_rate": len(selected) / 600.0, + "frontier_csv": str(frontier_path.resolve()), + "frontier_csv_sha256": sha256(frontier_path), + "real_requests_private": str(real_path.resolve()), + "real_requests_private_sha256": sha256(real_path), + "row_vector_sha256": vector_digest.hexdigest(), + } + ) + + failures = { + "input_length_mismatches": length_mismatches, + "source_hash_count_mismatches": source_hash_count_mismatches, + "runtime_identity_collisions": identity_collision_count, + "source_to_runtime_relation_conflicts": source_to_runtime_conflicts, + "runtime_to_source_relation_conflicts": runtime_to_source_conflicts, + } + manifest = { + "schema": "qwen30-exact-trace-block16-v1", + "status": "pass" if not any(failures.values()) else "fail", + "execution": { + "host": socket.gethostname(), + "python": platform.python_version(), + "transformers": transformers.__version__, + "tokenizer": type(tokenizer).__name__, + "elapsed_seconds": round(time.time() - started, 3), + }, + "source": { + "trace": str(args.trace.resolve()), + "trace_sha256": sha256(args.trace), + "requests": len(rows), + "eligible_requests": len(eligible), + "model": str(args.model.resolve()), + "max_model_len": args.max_model_len, + }, + "block_contract": { + "source_block_size": args.source_block_size, + "runtime_block_size": args.runtime_block_size, + "identity": "BLAKE2b-128(parent runtime identity, exact token-id block)", + "unique_runtime_identities": len(identity_to_digest), + "unique_source_relations": len(source_to_runtime), + "failures": failures, + }, + "selection_contract": ( + "eligible universe followed by source sampling_u threshold; no length " + "selection or output override; original arrivals/order preserved" + ), + "thresholds": threshold_manifests, + "privacy": "prompt text exists only under private/ and must not be harvested", + } + manifest_path = args.output_root / "public" / "manifest.json" + manifest_path.parent.mkdir(parents=True, exist_ok=True) + manifest_path.write_text(json.dumps(manifest, indent=2, sort_keys=True) + "\n") + print(json.dumps({"status": manifest["status"], "failures": failures, "thresholds": threshold_manifests}, sort_keys=True)) + if manifest["status"] != "pass": + raise SystemExit(1) + + +if __name__ == "__main__": + main() diff --git a/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/allreduce.json b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/allreduce.json new file mode 100644 index 0000000..aae1f0a --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/allreduce.json @@ -0,0 +1,824 @@ +{ + "environment": [ + { + "backend_env": { + "VLLM_ALLREDUCE_USE_FLASHINFER": "1", + "VLLM_FLASHINFER_ALLREDUCE_BACKEND": "trtllm" + }, + "gpu": "NVIDIA H20", + "model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B", + "torch_cuda": "12.9", + "torch_version": "2.11.0+cu129", + "vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1", + "vllm_version": "0.20.0" + }, + { + "backend_env": { + "VLLM_ALLREDUCE_USE_FLASHINFER": "1", + "VLLM_FLASHINFER_ALLREDUCE_BACKEND": "trtllm" + }, + "gpu": "NVIDIA H20", + "model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B", + "torch_cuda": "12.9", + "torch_version": "2.11.0+cu129", + "vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1", + "vllm_version": "0.20.0" + } + ], + "frontier_consumption": "diagnostic_only_in_base_profile_only_run; measured lookup requires a separate CC-backend injection ablation", + "rows": [ + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.08288000151515007, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 1, + "payload_bytes": 4096, + "per_rank_time_ms": [ + { + "max": 0.4872959852218628, + "mean": 0.1310015980154276, + "median": 0.07679999992251396, + "min": 0.06217600032687187, + "std": 0.12790721677293843 + }, + { + "max": 0.4402880072593689, + "mean": 0.12842560112476348, + "median": 0.08288000151515007, + "min": 0.0655680000782013, + "std": 0.11220176524616535 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.0793600007891655, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 8, + "payload_bytes": 32768, + "per_rank_time_ms": [ + { + "max": 0.12716799974441528, + "mean": 0.07871360033750534, + "median": 0.0759200006723404, + "min": 0.06032000109553337, + "std": 0.019331314939874535 + }, + { + "max": 0.12380799651145935, + "mean": 0.08059840016067028, + "median": 0.0793600007891655, + "min": 0.06217600032687187, + "std": 0.01687088356254092 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.0713919997215271, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 16, + "payload_bytes": 65536, + "per_rank_time_ms": [ + { + "max": 0.12697599828243256, + "mean": 0.0767391998320818, + "median": 0.07078400254249573, + "min": 0.05910399928689003, + "std": 0.018775178979463278 + }, + { + "max": 0.11430399864912033, + "mean": 0.07594559974968433, + "median": 0.0713919997215271, + "min": 0.06124800071120262, + "std": 0.015719922150631036 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.08056000247597694, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 32, + "payload_bytes": 131072, + "per_rank_time_ms": [ + { + "max": 0.1037760004401207, + "mean": 0.07954559996724128, + "median": 0.08056000247597694, + "min": 0.05955199897289276, + "std": 0.0135697420393132 + }, + { + "max": 0.10608000308275223, + "mean": 0.07971520014107228, + "median": 0.07593599706888199, + "min": 0.06028800085186958, + "std": 0.015319849772775456 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.0865279994904995, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 64, + "payload_bytes": 262144, + "per_rank_time_ms": [ + { + "max": 0.14470399916172028, + "mean": 0.09121599942445754, + "median": 0.0865279994904995, + "min": 0.06441599875688553, + "std": 0.024893837894277456 + }, + { + "max": 0.12438400089740753, + "mean": 0.08531199917197227, + "median": 0.08031999692320824, + "min": 0.06364800035953522, + "std": 0.01878029830059533 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.07135999947786331, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 128, + "payload_bytes": 524288, + "per_rank_time_ms": [ + { + "max": 0.11753600090742111, + "mean": 0.07606079950928687, + "median": 0.07135999947786331, + "min": 0.05843200162053108, + "std": 0.01755519771639284 + }, + { + "max": 0.1103999987244606, + "mean": 0.07607359997928143, + "median": 0.07073600217700005, + "min": 0.05721599981188774, + "std": 0.016904445220949783 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.07321599870920181, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 256, + "payload_bytes": 1048576, + "per_rank_time_ms": [ + { + "max": 0.11740799993276596, + "mean": 0.07749119997024537, + "median": 0.07203200086951256, + "min": 0.05862399935722351, + "std": 0.017701381594822835 + }, + { + "max": 0.11382400244474411, + "mean": 0.07733759954571724, + "median": 0.07321599870920181, + "min": 0.059039998799562454, + "std": 0.017188890882557036 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.09025600180029869, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 512, + "payload_bytes": 2097152, + "per_rank_time_ms": [ + { + "max": 0.13980799913406372, + "mean": 0.0950367994606495, + "median": 0.09025600180029869, + "min": 0.06815999746322632, + "std": 0.022829835127539378 + }, + { + "max": 0.14764800667762756, + "mean": 0.09710080176591873, + "median": 0.08720000088214874, + "min": 0.07152000069618225, + "std": 0.02500574954063789 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.08083200082182884, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 1024, + "payload_bytes": 4194304, + "per_rank_time_ms": [ + { + "max": 0.15574400126934052, + "mean": 0.08760640025138855, + "median": 0.07846399769186974, + "min": 0.07097599655389786, + "std": 0.024487311423551025 + }, + { + "max": 0.16284799575805664, + "mean": 0.08963519930839539, + "median": 0.08083200082182884, + "min": 0.07100799679756165, + "std": 0.026047320562445356 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.10891199856996536, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 2048, + "payload_bytes": 8388608, + "per_rank_time_ms": [ + { + "max": 0.1582079976797104, + "mean": 0.11541439890861512, + "median": 0.10836799815297127, + "min": 0.09062399715185165, + "std": 0.018285136316576037 + }, + { + "max": 0.1578879952430725, + "mean": 0.11537599861621857, + "median": 0.10891199856996536, + "min": 0.0960640013217926, + "std": 0.018246538626977286 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.1703840047121048, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 4096, + "payload_bytes": 16777216, + "per_rank_time_ms": [ + { + "max": 0.19327999651432037, + "mean": 0.1707327976822853, + "median": 0.1703840047121048, + "min": 0.14815999567508698, + "std": 0.014211056022719618 + }, + { + "max": 0.19276799261569977, + "mean": 0.1658592015504837, + "median": 0.16379200667142868, + "min": 0.14560000598430634, + "std": 0.013840249648693638 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.25539200007915497, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 8192, + "payload_bytes": 33554432, + "per_rank_time_ms": [ + { + "max": 0.2807359993457794, + "mean": 0.25750079900026324, + "median": 0.25539200007915497, + "min": 0.24624000489711761, + "std": 0.008925204570802302 + }, + { + "max": 0.2863999903202057, + "mean": 0.2585055992007256, + "median": 0.255280002951622, + "min": 0.24371199309825897, + "std": 0.012059738582656496 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 2 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.1021759994328022, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 1, + "payload_bytes": 4096, + "per_rank_time_ms": [ + { + "max": 0.9770879745483398, + "mean": 0.1974783968180418, + "median": 0.10099200159311295, + "min": 0.05913599953055382, + "std": 0.2660581738745569 + }, + { + "max": 0.892799973487854, + "mean": 0.18164799660444259, + "median": 0.1021759994328022, + "min": 0.06435199826955795, + "std": 0.23947520188197013 + }, + { + "max": 0.6467199921607971, + "mean": 0.15839359983801843, + "median": 0.10100800171494484, + "min": 0.06800000369548798, + "std": 0.16617013141866102 + }, + { + "max": 0.6725760102272034, + "mean": 0.15686400160193442, + "median": 0.10044800117611885, + "min": 0.06063999980688095, + "std": 0.17523222161300497 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.12694399803876877, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 8, + "payload_bytes": 32768, + "per_rank_time_ms": [ + { + "max": 0.6659520268440247, + "mean": 0.1927648030221462, + "median": 0.12694399803876877, + "min": 0.07609599828720093, + "std": 0.16697784531907736 + }, + { + "max": 0.695360004901886, + "mean": 0.19356480240821838, + "median": 0.11726400256156921, + "min": 0.0796160027384758, + "std": 0.17588096678867862 + }, + { + "max": 0.5939840078353882, + "mean": 0.1868800014257431, + "median": 0.12379200011491776, + "min": 0.07427199929952621, + "std": 0.1463231714943902 + }, + { + "max": 0.6635839939117432, + "mean": 0.1874335989356041, + "median": 0.12014400213956833, + "min": 0.07526399940252304, + "std": 0.16680959677760304 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.09161599725484848, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 16, + "payload_bytes": 65536, + "per_rank_time_ms": [ + { + "max": 0.12665599584579468, + "mean": 0.09443839862942696, + "median": 0.09124799817800522, + "min": 0.06431999802589417, + "std": 0.0205690155775906 + }, + { + "max": 0.1303039938211441, + "mean": 0.09712959825992584, + "median": 0.09161599725484848, + "min": 0.07648000121116638, + "std": 0.019072048129173236 + }, + { + "max": 0.13836799561977386, + "mean": 0.09821119979023933, + "median": 0.09148800000548363, + "min": 0.0727040022611618, + "std": 0.021314066545189116 + }, + { + "max": 0.12992000579833984, + "mean": 0.09272959977388381, + "median": 0.08931199833750725, + "min": 0.06406400352716446, + "std": 0.021360803830354765 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.08580800145864487, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 32, + "payload_bytes": 131072, + "per_rank_time_ms": [ + { + "max": 0.13449600338935852, + "mean": 0.08960640132427215, + "median": 0.08299200236797333, + "min": 0.06796800345182419, + "std": 0.020633597898445998 + }, + { + "max": 0.14735999703407288, + "mean": 0.09248319901525974, + "median": 0.08580800145864487, + "min": 0.05913599953055382, + "std": 0.025960234928829564 + }, + { + "max": 0.13705599308013916, + "mean": 0.08947199806571007, + "median": 0.08460799977183342, + "min": 0.0634239986538887, + "std": 0.02122838946992339 + }, + { + "max": 0.13846400380134583, + "mean": 0.0859104000031948, + "median": 0.08308799937367439, + "min": 0.05974400043487549, + "std": 0.022373631424433445 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.09867199882864952, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 64, + "payload_bytes": 262144, + "per_rank_time_ms": [ + { + "max": 0.1279039978981018, + "mean": 0.09748799875378608, + "median": 0.09678399935364723, + "min": 0.0655359998345375, + "std": 0.02315719144614622 + }, + { + "max": 0.1356479972600937, + "mean": 0.10018239840865135, + "median": 0.09532799944281578, + "min": 0.06185600161552429, + "std": 0.02330700253650042 + }, + { + "max": 0.13142399489879608, + "mean": 0.09778879955410957, + "median": 0.09492799639701843, + "min": 0.06560000032186508, + "std": 0.02307579212430045 + }, + { + "max": 0.1276479959487915, + "mean": 0.09611519873142242, + "median": 0.09867199882864952, + "min": 0.0642239972949028, + "std": 0.02273612181973431 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.09646400064229965, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 128, + "payload_bytes": 524288, + "per_rank_time_ms": [ + { + "max": 0.14060799777507782, + "mean": 0.09770880043506622, + "median": 0.09115200117230415, + "min": 0.06950400024652481, + "std": 0.024752645089849798 + }, + { + "max": 0.14377599954605103, + "mean": 0.09824960008263588, + "median": 0.08999999985098839, + "min": 0.07103999704122543, + "std": 0.025403407389046027 + }, + { + "max": 0.13680000603199005, + "mean": 0.09993600100278854, + "median": 0.09646400064229965, + "min": 0.06790400296449661, + "std": 0.022297424273985882 + }, + { + "max": 0.1391039937734604, + "mean": 0.09769919961690902, + "median": 0.09601600095629692, + "min": 0.06835199892520905, + "std": 0.023899922100804445 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.08377600088715553, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 256, + "payload_bytes": 1048576, + "per_rank_time_ms": [ + { + "max": 0.1464959979057312, + "mean": 0.09276160076260567, + "median": 0.08377600088715553, + "min": 0.06777600198984146, + "std": 0.024751086465295658 + }, + { + "max": 0.14319999516010284, + "mean": 0.09080640003085136, + "median": 0.080400001257658, + "min": 0.06796800345182419, + "std": 0.023365718881708488 + }, + { + "max": 0.1382399946451187, + "mean": 0.09063360020518303, + "median": 0.08193599805235863, + "min": 0.06627199798822403, + "std": 0.02372618650854302 + }, + { + "max": 0.14313599467277527, + "mean": 0.09044799953699112, + "median": 0.08128000050783157, + "min": 0.06652799993753433, + "std": 0.02462486862033686 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.1128000020980835, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 512, + "payload_bytes": 2097152, + "per_rank_time_ms": [ + { + "max": 0.1600320041179657, + "mean": 0.11426239982247352, + "median": 0.1128000020980835, + "min": 0.07657600194215775, + "std": 0.030240087702350687 + }, + { + "max": 0.15881599485874176, + "mean": 0.11206399947404862, + "median": 0.10628800094127655, + "min": 0.0772159993648529, + "std": 0.029933135345483627 + }, + { + "max": 0.15612800419330597, + "mean": 0.10761600062251091, + "median": 0.09860799834132195, + "min": 0.07689599692821503, + "std": 0.02634237020678647 + }, + { + "max": 0.15865600109100342, + "mean": 0.11094079986214637, + "median": 0.10979199782013893, + "min": 0.07583999633789062, + "std": 0.028619217028542445 + } + ], + "selected_backend": "flashinfer_trtllm", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.08755199983716011, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 1024, + "payload_bytes": 4194304, + "per_rank_time_ms": [ + { + "max": 0.11999999731779099, + "mean": 0.0843871995806694, + "median": 0.08755199983716011, + "min": 0.06332799792289734, + "std": 0.016638543890716024 + }, + { + "max": 0.1218239963054657, + "mean": 0.08518079966306687, + "median": 0.08032000064849854, + "min": 0.06393600255250931, + "std": 0.019900899429956945 + }, + { + "max": 0.11849600076675415, + "mean": 0.0843968003988266, + "median": 0.08702399954199791, + "min": 0.06297600269317627, + "std": 0.017031908773433545 + }, + { + "max": 0.12300799787044525, + "mean": 0.0846304003149271, + "median": 0.08139199763536453, + "min": 0.06195199862122536, + "std": 0.020106523698622265 + } + ], + "selected_backend": "nccl_fallback", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.12361599877476692, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 2048, + "payload_bytes": 8388608, + "per_rank_time_ms": [ + { + "max": 0.17155200242996216, + "mean": 0.12168959975242614, + "median": 0.12055999785661697, + "min": 0.09609600156545639, + "std": 0.022565485532483928 + }, + { + "max": 0.9246399998664856, + "mean": 0.19978560134768486, + "median": 0.12361599877476692, + "min": 0.09715200215578079, + "std": 0.24230694305662265 + }, + { + "max": 0.9317439794540405, + "mean": 0.20037759989500045, + "median": 0.12327999994158745, + "min": 0.09603200107812881, + "std": 0.24450903278000383 + }, + { + "max": 0.9321280121803284, + "mean": 0.19875840097665787, + "median": 0.12230399996042252, + "min": 0.0950080007314682, + "std": 0.24519252220785093 + } + ], + "selected_backend": "nccl_fallback", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.20030399411916733, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 4096, + "payload_bytes": 16777216, + "per_rank_time_ms": [ + { + "max": 0.3261440098285675, + "mean": 0.20826880186796187, + "median": 0.19974400103092194, + "min": 0.1409280002117157, + "std": 0.051397264855718945 + }, + { + "max": 0.3248000144958496, + "mean": 0.20548800230026246, + "median": 0.1979840025305748, + "min": 0.141184002161026, + "std": 0.04980002399656717 + }, + { + "max": 0.32547199726104736, + "mean": 0.21280319690704347, + "median": 0.20030399411916733, + "min": 0.14127999544143677, + "std": 0.05304243085685509 + }, + { + "max": 0.26047998666763306, + "mean": 0.1969312012195587, + "median": 0.18079999834299088, + "min": 0.14057600498199463, + "std": 0.042174123638424224 + } + ], + "selected_backend": "nccl_fallback", + "tensor_parallel_size": 4 + }, + { + "communicator": "vllm.tensor_model_parallel_all_reduce", + "critical_path_median_ms": 0.2924960106611252, + "dtype": "bfloat16", + "hidden_dim": 2048, + "num_tokens": 8192, + "payload_bytes": 33554432, + "per_rank_time_ms": [ + { + "max": 0.45052799582481384, + "mean": 0.3013375997543335, + "median": 0.28273600339889526, + "min": 0.21334399282932281, + "std": 0.07214223764527236 + }, + { + "max": 0.4466240108013153, + "mean": 0.2968191936612129, + "median": 0.27796798944473267, + "min": 0.21241599321365356, + "std": 0.07400678240849741 + }, + { + "max": 0.3830080032348633, + "mean": 0.2946112036705017, + "median": 0.2924960106611252, + "min": 0.21084800362586975, + "std": 0.05323627615746332 + }, + { + "max": 0.4609600007534027, + "mean": 0.3054272010922432, + "median": 0.289792001247406, + "min": 0.21062399446964264, + "std": 0.07608482904865672 + } + ], + "selected_backend": "nccl_fallback", + "tensor_parallel_size": 4 + } + ], + "schema_version": "qwen30_vllm020_allreduce_frozen.v1" +} diff --git a/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/attention.csv b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/attention.csv new file mode 100644 index 0000000..a8101ec --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/attention.csv @@ -0,0 +1,151 @@ +time_stats.attn_input_reshape.min,time_stats.attn_input_reshape.max,time_stats.attn_input_reshape.mean,time_stats.attn_input_reshape.median,time_stats.attn_input_reshape.std,time_stats.attn_kv_cache_save.min,time_stats.attn_kv_cache_save.max,time_stats.attn_kv_cache_save.mean,time_stats.attn_kv_cache_save.median,time_stats.attn_kv_cache_save.std,time_stats.attn_prefill.min,time_stats.attn_prefill.max,time_stats.attn_prefill.mean,time_stats.attn_prefill.median,time_stats.attn_prefill.std,time_stats.attn_decode.min,time_stats.attn_decode.max,time_stats.attn_decode.mean,time_stats.attn_decode.median,time_stats.attn_decode.std,time_stats.attn_output_reshape.min,time_stats.attn_output_reshape.max,time_stats.attn_output_reshape.mean,time_stats.attn_output_reshape.median,time_stats.attn_output_reshape.std,n_embd,n_q_head,n_kv_head,block_size,num_tensor_parallel_workers,max_model_len,batch_size,prefill_chunk_size,kv_cache_size,is_prefill,attention_backend,is_mixed_batch,mode,seq_lens,total_tokens,max_seq_len,min_seq_len,avg_seq_len,equal_seq_len,seq_len_variance,seq_len_std,seq_len_cv,is_chunked_prefill_sample,chunk_start_token,chunk_end_token,total_prefill_tokens,profiling_precision,model_arch,quant_signature,measurement_type,is_true_mixed_batch,prefill_seq_lens,prefill_kv_cache_sizes,decode_kv_cache_sizes,num_prefill_seqs,num_decode_seqs,decode_batch_size,total_batch_size,total_decode_tokens,decode_avg_kv_cache_size,batch_composition_ratio,batch_spec,projection_policy +0.0,0.0,0.0,0.0,0.0,0.01414399966597557,0.028863999992609024,0.019705599918961526,0.01771199982613325,0.005157200849836681,0.047968000173568726,0.07046400010585785,0.05810240097343922,0.05810240097343922,0.007477463486041561,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,64,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,False,0.0,64.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.04947200044989586,0.020412799902260303,0.01635199971497059,0.010107497379722417,0.046560000628232956,0.08323200047016144,0.05587520003318787,0.05587520003318787,0.011126758739503428,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,128,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,False,0.0,128.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.022207999601960182,0.017033600155264138,0.015312000177800655,0.002819235991970241,0.05104000121355057,0.07692799717187881,0.056396800279617305,0.056396800279617305,0.007481982178637539,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,256,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,False,0.0,256.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015072000212967396,0.022272000089287758,0.01706880023702979,0.01616000011563301,0.002460889579319197,0.06931199878454208,0.0838719978928566,0.07432000041007995,0.07432000041007995,0.004777766433175866,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,512,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,False,0.0,512.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.018592000007629395,0.028543999418616295,0.02095999978482723,0.019183999858796597,0.003198175496053494,0.12179200351238251,0.15408000349998474,0.1307712011039257,0.1307712011039257,0.00858807797538298,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.027775999158620834,0.03385600075125694,0.030131200328469276,0.029680000618100166,0.0021152558103575215,0.32678401470184326,0.3450239896774292,0.33396480381488797,0.33396480381488797,0.0045872424917606375,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.04438399896025658,0.05084799975156784,0.046540799736976626,0.04531199857592583,0.002277905811237223,1.0959680080413818,1.1151360273361206,1.0999775886535645,1.0999775886535645,0.005694403246120485,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.078015998005867,0.08691199868917465,0.08114239946007729,0.08019199967384338,0.00292795706334475,4.070400238037109,4.113152027130127,4.087088012695312,4.087088012695312,0.013660567012509554,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.016063999384641647,0.05167999863624573,0.022115200012922286,0.017583999782800674,0.010340094822340818,0.05196800082921982,0.09011200070381165,0.06328320093452933,0.06328320093452933,0.012557341255467452,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,64,448.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,True,448.0,512.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64s512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01583999954164028,0.026623999699950218,0.018927999772131443,0.017376000061631203,0.003514650316260619,0.06681600213050842,0.07993599772453308,0.0725280001759529,0.0725280001759529,0.004343502558613716,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,128,896.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,True,896.0,1024.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01648000068962574,0.030880000442266464,0.01945280022919178,0.017967999912798405,0.004096211183007485,0.1311360001564026,0.1546880006790161,0.13908160030841826,0.13908160030841826,0.007511906874366178,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,256,1792.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,True,1792.0,2048.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.017855999991297722,0.03558399900794029,0.020851199887692927,0.018559999763965607,0.005235911594130716,0.32950401306152344,0.350271999835968,0.33912960588932034,0.33912960588932034,0.006027400986663648,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,512,3584.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,3584.0,4096.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.019328000023961067,0.040608000010252,0.022790400311350822,0.020704000256955624,0.006113051965778337,1.1415679454803467,1.1518720388412476,1.144483208656311,1.144483208656311,0.0032332311374389127,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,1024,7168.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,True,7168.0,8192.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1ks8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015807999297976494,0.030688000842928886,0.019596799835562707,0.01774400006979704,0.004343384771033462,0.0,0.0,0.0,0.0,0.0,0.049056001007556915,0.07580800354480743,0.05948160067200661,0.05948160067200661,0.009031541471446955,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01603199914097786,0.02486399933695793,0.01923839971423149,0.018079999834299088,0.0032282528537266424,0.0,0.0,0.0,0.0,0.0,0.05142400041222572,0.07353600114583969,0.059328000620007516,0.059328000620007516,0.0073307807735143084,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.016543999314308167,0.03977600112557411,0.021379199624061585,0.018511999398469925,0.006593576176246171,0.0,0.0,0.0,0.0,0.0,0.0488319993019104,0.06435199826955795,0.05479039996862411,0.05479039996862411,0.005672522998491864,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01635199971497059,0.02844800055027008,0.019267200119793416,0.017952000722289085,0.0035068687666949577,0.0,0.0,0.0,0.0,0.0,0.049855999648571014,0.07798399776220322,0.05986879989504815,0.05986879989504815,0.01043914754878828,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.016383999958634377,0.026079999282956123,0.01923519968986511,0.017791999503970146,0.0032161974331284568,0.0,0.0,0.0,0.0,0.0,0.058111999183893204,0.1045759990811348,0.06708480007946492,0.06708480007946492,0.013479022462646494,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.04057599976658821,0.019100800156593323,0.015455999877303839,0.007512281243011577,0.0,0.0,0.0,0.0,0.0,0.05363199859857559,0.07782399654388428,0.06090559959411622,0.06090559959411622,0.007544620176348091,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.02191999927163124,0.016684799920767546,0.01563199982047081,0.0024293118621811216,0.0,0.0,0.0,0.0,0.0,0.0629120022058487,0.07891199737787247,0.06891520097851753,0.06891520097851753,0.005472695665695425,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014560000039637089,0.038943998515605927,0.018313600029796363,0.01561600062996149,0.007127270260115769,0.0,0.0,0.0,0.0,0.0,0.08675199747085571,0.10662399977445602,0.09391999915242194,0.09391999915242194,0.006988099589086635,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.054687999188899994,0.021439999900758268,0.01539199985563755,0.012052764849597775,0.0,0.0,0.0,0.0,0.0,0.13488000631332397,0.1528639942407608,0.1431359991431236,0.1431359991431236,0.005436271464033599,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.041919998824596405,0.01899839974939823,0.015343999955803156,0.007989843526623287,0.0,0.0,0.0,0.0,0.0,0.06176000088453293,0.08374399691820145,0.06747519969940186,0.06747519969940186,0.0066067747128778,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.016256000846624374,0.11353600025177002,0.042761600017547606,0.028960000723600388,0.029104301538020762,0.0,0.0,0.0,0.0,0.0,0.09734400361776352,0.14422400295734406,0.11392960175871848,0.11392960175871848,0.013198594600417867,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.034143999218940735,0.018918400071561335,0.01643200032413006,0.005500943993080684,0.0,0.0,0.0,0.0,0.0,0.12918399274349213,0.15087999403476715,0.13807999789714814,0.13807999789714814,0.007658330538677587,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.016063999384641647,0.03641600161790848,0.0198208000510931,0.01780799962580204,0.0057264128169845765,0.0,0.0,0.0,0.0,0.0,0.22099199891090393,0.23904000222682953,0.2293503984808922,0.2293503984808922,0.004861342907006028,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.035840000957250595,0.018908800091594458,0.015792000107467175,0.0064374817924757475,0.0,0.0,0.0,0.0,0.0,0.10134399682283401,0.12201599776744843,0.10896319895982742,0.10896319895982742,0.006336330809165179,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.03417599946260452,0.017846399918198586,0.014800000004470348,0.006495007539635255,0.0,0.0,0.0,0.0,0.0,0.13126400113105774,0.15561600029468536,0.1389280006289482,0.1389280006289482,0.008381472811075022,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.03519999980926514,0.019168000388890504,0.01600000075995922,0.005995522477654695,0.0,0.0,0.0,0.0,0.0,0.21728000044822693,0.2343679964542389,0.2231455981731415,0.2231455981731415,0.004720730646739123,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014047999866306782,0.03670400008559227,0.018441599886864425,0.015023999847471714,0.006596535162793127,0.0,0.0,0.0,0.0,0.0,0.39321601390838623,0.4524799883365631,0.4058080047369003,0.4058080047369003,0.01578349755088941,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.022143999114632607,0.016912000067532063,0.015168000012636185,0.0028156089295136347,0.0,0.0,0.0,0.0,0.0,0.15587200224399567,0.3079040050506592,0.17838079929351805,0.17838079929351805,0.04355865575265927,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.02112000063061714,0.015516800060868263,0.01488000014796853,0.001940870731593904,0.0,0.0,0.0,0.0,0.0,0.21587200462818146,0.23561599850654602,0.22250880002975468,0.22250880002975468,0.006181951170646666,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015552000142633915,0.039264000952243805,0.023609600123018028,0.02131200022995472,0.007236979625711548,0.0,0.0,0.0,0.0,0.0,0.408735990524292,0.470335990190506,0.4336863994598388,0.4336863994598388,0.01844662383160074,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.025407999753952026,0.016227199975401164,0.014960000291466713,0.0031617375441736185,0.0,0.0,0.0,0.0,0.0,0.7412800192832947,0.7627840042114258,0.7464000046253203,0.7464000046253203,0.006112167448837547,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01462399959564209,0.02812799997627735,0.020652799773961304,0.021359999664127827,0.004308706957613102,0.028383498565450627,0.039859687970646644,0.032492258074592426,0.032492258074592426,0.00453597266208597,0.029312501176103633,0.04116431058787463,0.03355574193327539,0.03355574193327539,0.004684436757701648,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,72,,,,,,,,False,,,64,BF16,generic,none,CUDA_EVENT,True,[64],[0],"[512, 512, 512, 512, 512, 512, 512, 512]",1,8,8,9,8,512.0,0.1111111111111111,q64_8q1s512,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.015552000142633915,0.034143999218940735,0.023171199765056372,0.024255999363958836,0.005908614918096971,0.03333159243114438,0.038935341782478095,0.03580428402241854,0.03580428402241854,0.002082270297044095,0.03633240903369937,0.04244065945634484,0.03902771507087562,0.03902771507087562,0.0022697354261490147,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,136,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,8,8,9,8,1024.0,0.1111111111111111,q128_8q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.02611199952661991,0.019635199941694735,0.018112000077962875,0.0038298050749257795,0.04189529417991216,0.057484239920526384,0.04744885718421094,0.04744885718421094,0.004779830748455743,0.051672703037266184,0.07089975418195164,0.05852234134479412,0.05852234134479412,0.005895334539786378,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,144,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,16,16,17,16,1024.0,0.058823529411764705,q128_16q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.029311999678611755,0.018662399891763926,0.01673599984496832,0.0044017112162725355,0.04322973959325901,0.05049827064705393,0.04535414343408448,0.04535414343408448,0.0022944156000240697,0.08733025617719538,0.10201372836398578,0.09162185574241775,0.09162185574241775,0.004635047631846023,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,272,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,16,16,17,16,2048.0,0.058823529411764705,q256_16q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014592000283300877,0.026367999613285065,0.016336000058799982,0.01515199989080429,0.003415353455946402,0.06031842775160765,0.06618323188375198,0.06274415549817247,0.06274415549817247,0.001985647289644255,0.14768157653992678,0.16204076249052324,0.15362064543185072,0.15362064543185072,0.004861590945216247,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,288,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,32,32,33,32,2048.0,0.030303030303030304,q256_32q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.02454400062561035,0.017167999967932702,0.016191999427974224,0.0028685016454498436,0.09128700688359712,0.09689150775996329,0.09360396051475776,0.09360396051475776,0.0013477542744916764,0.2740889887523892,0.2909164873209846,0.2810456356995366,0.2810456356995366,0.004046628526808561,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,544,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q512_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.01881599985063076,0.03097599931061268,0.024598400108516216,0.024848000146448612,0.0037539437391565975,0.1035249255866932,0.10603132147437412,0.10399797220840973,0.10399797220840973,0.0007025109429056814,0.5652750707893444,0.5789606938874117,0.5678580377517648,0.5678580377517648,0.003835906384194897,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,576,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,64,64,65,64,4096.0,0.015384615384615385,q512_64q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.018624000251293182,0.043487999588251114,0.024460799992084503,0.019600000232458115,0.008922081629781394,0.196169204945307,0.2076140047945799,0.2008444429250931,0.2008444429250931,0.00394350953292805,1.1196708009293268,1.1849940417370974,1.1463555573610091,1.1463555573610091,0.022508285530529783,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192]",1,64,64,65,64,8192.0,0.015384615384615385,q1k_64q1s8k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.027135999873280525,0.03667199984192848,0.02945920005440712,0.028256000019609928,0.0029446678408169553,0.37757279619664613,0.3898113624476372,0.38075520430942184,0.38075520430942184,0.0036600203831042254,0.2522831942132049,0.2604606493092597,0.25440958703617433,0.25440958703617433,0.0024455194930253126,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q2k_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.0435199998319149,0.049695998430252075,0.04502719938755036,0.04395199939608574,0.002035785660169308,1.1048984388245497,1.1189053886476108,1.1112371236754128,1.1112371236754128,0.0050220696724624985,0.1395495077239122,0.14131859607071193,0.14035008841031085,0.14035008841031085,0.0006342911944856293,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,16,16,17,16,4096.0,0.058823529411764705,q4k_16q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.018783999606966972,0.024288000538945198,0.020627199858427047,0.019567999988794327,0.0019457052717059358,0.09455999732017517,0.12185599654912949,0.10207359939813614,0.10207359939813614,0.00753346544014261,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,2,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512]",1024,512,512,512.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.027295999228954315,0.034752000123262405,0.02943360023200512,0.028528000228106976,0.0023159160681123767,0.14416000247001648,0.15904000401496887,0.14979200065135959,0.14979200065135959,0.00480624675866005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,4,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512]",2048,512,512,512.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.043455999344587326,0.05084799975156784,0.045500800386071204,0.04411200061440468,0.002490556062831049,0.24454399943351746,0.25865599513053894,0.2504959970712662,0.2504959970712662,0.003778494140301353,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512]",4096,512,512,512.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.07673600316047668,0.08374399691820145,0.07970559895038605,0.07873599976301193,0.0022907976135004057,0.445248007774353,0.4758400022983551,0.45409599840641024,0.45409599840641024,0.009133230340383306,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512]",8192,512,512,512.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.043296001851558685,0.051072001457214355,0.044972800090909,0.04399999976158142,0.002451216824441962,0.6147199869155884,0.6290879845619202,0.6204927921295166,0.6204927921295166,0.004344846739788608,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,2,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048]",4096,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.07737600058317184,0.09123200178146362,0.08094720020890236,0.07980800047516823,0.004065264798368611,1.1744320392608643,1.1887680292129517,1.178323209285736,1.178323209285736,0.004395876469319665,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,4,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048, 2048, 2048]",8192,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.02364799939095974,0.01809599995613098,0.016352000646293163,0.0035481127058959038,0.04822399839758873,0.08566399663686752,0.05961279980838299,0.05961279980838299,0.011445665413968877,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,64,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,False,0.0,64.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.020864000543951988,0.01668160008266568,0.015664000064134598,0.0025769063833097584,0.049695998430252075,0.08057600259780884,0.05882879942655563,0.05882879942655563,0.009515126108519331,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,128,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,False,0.0,128.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.028704000636935234,0.017430400010198355,0.015056000091135502,0.004349294613335555,0.049855999648571014,0.07366400212049484,0.05459520071744919,0.05459520071744919,0.0069610920757925574,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,256,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,False,0.0,256.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.03161599859595299,0.017788799852132796,0.015711999963968992,0.005005385723318659,0.06102399900555611,0.08179199695587158,0.06650560013949873,0.06650560013949873,0.006947995595801105,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,512,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,False,0.0,512.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.04416000097990036,0.019200000166893005,0.015488000120967627,0.008561241323364038,0.08054400235414505,0.09196799993515015,0.08607039973139763,0.08607039973139763,0.004145329035483754,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.017855999991297722,0.023391999304294586,0.019667199812829494,0.018463999964296818,0.0022577669687832585,0.18729600310325623,0.20585599541664124,0.19546559900045393,0.19546559900045393,0.006339068824303663,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.026240000501275063,0.03446400165557861,0.028297600522637367,0.027088000439107418,0.0025148441522922374,0.5754240155220032,0.5889919996261597,0.5800191938877105,0.5800191938877105,0.003858869273829596,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.04182400181889534,0.047200001776218414,0.043036799877882004,0.0423360001295805,0.0017073405772076728,2.063199996948242,2.0787200927734375,2.067151999473572,2.067151999473572,0.004959651271127835,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.05648000165820122,0.02270399993285537,0.017935999669134617,0.012377915150727689,0.049536000937223434,0.07196799665689468,0.056015999615192415,0.056015999615192415,0.0070476637552742884,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,64,448.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,True,448.0,512.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64s512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01408000010997057,0.021344000473618507,0.01611520005390048,0.014928000047802925,0.0025499884993961702,0.07072000205516815,0.2642880082130432,0.1588256008923054,0.1588256008923054,0.053220347086102376,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,128,896.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,True,896.0,1024.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01360000018030405,0.03014400042593479,0.016975999902933837,0.015056000091135502,0.004715159697364111,0.08393599838018417,0.11036799848079681,0.09160000011324881,0.09160000011324881,0.007911669434472792,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,256,1792.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,True,1792.0,2048.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.020767999812960625,0.016233599931001663,0.015392000321298838,0.002202615907995427,0.1998399943113327,0.22070400416851044,0.20855360180139543,0.20855360180139543,0.00689307200230667,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,512,3584.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,3584.0,4096.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.033440001308918,0.018684800155460833,0.016048000194132328,0.00553991005639174,0.6043199896812439,0.635807991027832,0.6126143991947173,0.6126143991947173,0.008745933953408096,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,1024,7168.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,True,7168.0,8192.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1ks8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.013824000023305416,0.03359999880194664,0.017811199743300678,0.014944000169634819,0.005926140483565472,0.0,0.0,0.0,0.0,0.0,0.045471999794244766,0.07539200037717819,0.054758400097489356,0.054758400097489356,0.010253548506101549,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014047999866306782,0.02409599907696247,0.01641279999166727,0.01473599998280406,0.003347158638713987,0.0,0.0,0.0,0.0,0.0,0.0461760014295578,0.07529599964618683,0.05460800044238568,0.05460800044238568,0.009748937798340135,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.028416000306606293,0.018611199874430894,0.01598400017246604,0.005209875093863647,0.0,0.0,0.0,0.0,0.0,0.048128001391887665,0.07897599786520004,0.061353600397706036,0.061353600397706036,0.010488153655157845,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014112000353634357,0.025728000327944756,0.016092800162732603,0.01512000011280179,0.003300888123052605,0.0,0.0,0.0,0.0,0.0,0.04864000156521797,0.07648000121116638,0.05810560062527656,0.05810560062527656,0.009473544218404408,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.03551999852061272,0.018588799890130757,0.016064000315964222,0.006071057437992447,0.0,0.0,0.0,0.0,0.0,0.04822399839758873,0.07862400263547897,0.05660480037331582,0.05660480037331582,0.009565394213730401,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014303999952971935,0.028831999748945236,0.01699519995599985,0.015024000313133001,0.004285000744868188,0.0,0.0,0.0,0.0,0.0,0.04854400083422661,0.06719999760389328,0.05778240002691746,0.05778240002691746,0.006852125554679805,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.0144640002399683,0.024927999824285507,0.0161183999851346,0.01521599991247058,0.0029774808524673907,0.0,0.0,0.0,0.0,0.0,0.05379199981689453,0.08966399729251862,0.06270079985260964,0.06270079985260964,0.009983591277092696,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.03001599945127964,0.017648000083863736,0.01547200046479702,0.004585126309484848,0.0,0.0,0.0,0.0,0.0,0.061664000153541565,0.07692799717187881,0.06704320013523103,0.06704320013523103,0.005500191798490629,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.026367999613285065,0.016947199776768684,0.015039999969303608,0.0037951566103550205,0.0,0.0,0.0,0.0,0.0,0.08799999952316284,0.111455999314785,0.0964031994342804,0.0964031994342804,0.007397541615558088,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01369599997997284,0.021247999742627144,0.015359999984502793,0.014640000183135271,0.0020942770950814317,0.0,0.0,0.0,0.0,0.0,0.051711998879909515,0.07065600156784058,0.058054400235414506,0.058054400235414506,0.006633034815910025,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014208000153303146,0.0307839997112751,0.017148799914866685,0.015039999969303608,0.004882374686312284,0.0,0.0,0.0,0.0,0.0,0.061919998377561576,0.07843200117349625,0.06628479920327664,0.06628479920327664,0.004962852689801192,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.013887999579310417,0.02969600073993206,0.017500799987465142,0.015232000034302473,0.00467273319705314,0.0,0.0,0.0,0.0,0.0,0.08819200098514557,0.11097600311040878,0.09493440166115762,0.09493440166115762,0.007509235042985577,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.022112000733613968,0.01751680001616478,0.016047999262809753,0.0030306621792915785,0.0,0.0,0.0,0.0,0.0,0.13065600395202637,0.15110400319099426,0.13857279866933822,0.13857279866933822,0.00750137841249771,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.013919999822974205,0.04012800008058548,0.01892479993402958,0.01550400024279952,0.007459545267816961,0.0,0.0,0.0,0.0,0.0,0.06278400123119354,0.08259200304746628,0.0704512007534504,0.0704512007534504,0.005979055984382744,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.02236800082027912,0.016332800220698118,0.014928000047802925,0.002784044363186731,0.0,0.0,0.0,0.0,0.0,0.1003199964761734,0.1279360055923462,0.10921279862523078,0.10921279862523078,0.00862769617046716,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.013919999822974205,0.0225600004196167,0.016128000058233737,0.014800000004470348,0.002958953332547708,0.0,0.0,0.0,0.0,0.0,0.13116799294948578,0.14812800288200378,0.13783999979496003,0.13783999979496003,0.005696384361148053,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014208000153303146,0.029983999207615852,0.017468800116330386,0.01508800033479929,0.0047379550962483065,0.0,0.0,0.0,0.0,0.0,0.217631995677948,0.2447360008955002,0.22715839892625808,0.22715839892625808,0.008831828221847138,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014047999866306782,0.02304000034928322,0.016512000095099212,0.014512000139802694,0.0035026774828624254,0.0,0.0,0.0,0.0,0.0,0.11020799726247787,0.12307199835777283,0.11600959971547126,0.11600959971547126,0.004667637266950902,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014112000353634357,0.042080000042915344,0.017510399967432023,0.014607999939471483,0.00823117883530167,0.0,0.0,0.0,0.0,0.0,0.15702399611473083,0.17587199807167053,0.16399359852075576,0.16399359852075576,0.006588299074676393,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.013919999822974205,0.0208320003002882,0.015299199987202883,0.01462399959564209,0.001916768086505386,0.0,0.0,0.0,0.0,0.0,0.21779200434684753,0.2415360063314438,0.2260768011212349,0.2260768011212349,0.007251352080685236,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014015999622642994,0.021088000386953354,0.015619200188666582,0.01473599998280406,0.002013227452302141,0.0,0.0,0.0,0.0,0.0,0.3959999978542328,0.4152640104293823,0.40332479774951924,0.40332479774951924,0.006942401431914052,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.03379200026392937,0.020595200080424547,0.019600000232458115,0.006548754248881344,0.026192623739694512,0.040006882507168426,0.029155180178492036,0.029155180178492036,0.00408828748438241,0.024591375524545756,0.037561119537986146,0.027372820355088746,0.027372820355088746,0.0038383559348575944,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,72,,,,,,,,False,,,64,BF16,generic,none,CUDA_EVENT,True,[64],[0],"[512, 512, 512, 512, 512, 512, 512, 512]",1,8,8,9,8,512.0,0.1111111111111111,q64_8q1s512,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.020896000787615776,0.015318400040268899,0.014431999996304512,0.0019640312960926966,0.029349018208693862,0.06236262941356679,0.03714313592014963,0.03714313592014963,0.009618313791872569,0.028826981462526914,0.06125337308649041,0.036482463672774496,0.036482463672774496,0.009447230957011863,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,136,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,8,8,9,8,1024.0,0.1111111111111111,q128_8q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.032127998769283295,0.017286399938166143,0.014479999896138906,0.005536495446636193,0.03273085874558354,0.04394578491937082,0.03563837490653034,0.03563837490653034,0.003429601730256567,0.03488514202593899,0.04683821345079978,0.037984025407085474,0.037984025407085474,0.0036553316361902684,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,144,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,16,16,17,16,1024.0,0.058823529411764705,q128_16q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.021503999829292297,0.015078400075435639,0.01425600005313754,0.002238435975478849,0.042100813549974185,0.051784144690147756,0.045378692890289625,0.045378692890289625,0.003184109940650555,0.05111518843748309,0.06287185663927425,0.05509490773570219,0.05509490773570219,0.0038658725544299132,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,272,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,16,16,17,16,2048.0,0.058823529411764705,q256_16q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.02687999978661537,0.017667199857532977,0.01566399959847331,0.003864811846387173,0.048475323773821306,0.05599956978723733,0.05123499252968345,0.05123499252968345,0.002427379820423941,0.08429268135885387,0.09737642835214408,0.0890914090616175,0.0890914090616175,0.0042209177332077005,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,288,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,32,32,33,32,2048.0,0.030303030303030304,q256_32q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.01462399959564209,0.03359999880194664,0.019804799742996693,0.016032000072300434,0.006750519908145474,0.07121508474579985,0.07292308367136396,0.07194410845270183,0.07194410845270183,0.0005500065915943844,0.14760091249712767,0.15114092373010238,0.14911189243564577,0.14911189243564577,0.0011399477384397005,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,544,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q512_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.021856000646948814,0.016835200227797033,0.015263999812304974,0.00283854448975065,0.08146338272142935,0.08560865714384096,0.0834932625520734,0.0834932625520734,0.0012259635905347874,0.2782486219401307,0.29240733788179385,0.2851819365989658,0.2851819365989658,0.004187435731481665,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,576,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,64,64,65,64,4096.0,0.015384615384615385,q512_64q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.04495999962091446,0.02143679987639189,0.015856000129133463,0.009709987872683342,0.1194459208702178,0.12302524755181463,0.12053885718696096,0.12053885718696096,0.001005118119341339,0.5597220650459199,0.5764947443228802,0.5648435507167102,0.5648435507167102,0.004709970715400788,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192]",1,64,64,65,64,8192.0,0.015384615384615385,q1k_64q1s8k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.018112000077962875,0.026496000587940216,0.019318400137126445,0.018432000651955605,0.0024249605112359905,0.19770253574610402,0.222811797868348,0.2054811520619412,0.2054811520619412,0.008000944254868043,0.13941746080159492,0.157124211777114,0.14490284788179197,0.14490284788179197,0.005642170080515992,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q2k_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.02595200017094612,0.03155200183391571,0.02727359998971224,0.026575999334454536,0.0016260948764843166,0.6014684881116659,0.6095472988212,0.6046757700946376,0.6046757700946376,0.0023537435563177303,0.11325152264578045,0.11477269562841545,0.11385542721485654,0.11385542721485654,0.0004431903698023628,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,16,16,17,16,4096.0,0.058823529411764705,q4k_16q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014303999952971935,0.03359999880194664,0.01814719969406724,0.015375999733805656,0.005678506740662529,0.06774400174617767,0.07891199737787247,0.07312640026211739,0.07312640026211739,0.003826583051422731,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,2,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512]",1024,512,512,512.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01788800023496151,0.028543999418616295,0.021340799890458582,0.019504000432789326,0.003718627037219618,0.09548799693584442,0.1327359974384308,0.10823359936475753,0.10823359936475753,0.013230635292043864,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,4,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512]",2048,512,512,512.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.02627200074493885,0.030368000268936157,0.027184000052511693,0.02643200010061264,0.0013545679205210022,0.14364799857139587,0.1597760021686554,0.15008639842271806,0.15008639842271806,0.005367723415171222,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512]",4096,512,512,512.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.04150399938225746,0.04726399853825569,0.042950399965047834,0.04224000126123428,0.001720147501765378,0.2433920055627823,0.28963199257850647,0.2549152016639709,0.2549152016639709,0.013450991019687407,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512]",8192,512,512,512.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.025887999683618546,0.03407999873161316,0.028303999826312064,0.026367999613285065,0.0028877495368841042,0.325439989566803,0.3441599905490875,0.33442879617214205,0.33442879617214205,0.005693597811441922,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,2,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048]",4096,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.04137599840760231,0.05084799975156784,0.044828799366950986,0.043087998405098915,0.003560363865797613,0.6110399961471558,0.6421759724617004,0.6204223990440368,0.6204223990440368,0.011214490370794758,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,4,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048, 2048, 2048]",8192,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014560000039637089,0.022784000262618065,0.016435200069099664,0.015519999898970127,0.0023688301421469523,0.04879999905824661,0.09139200299978256,0.06054079942405224,0.06054079942405224,0.012152608702448775,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,64,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,False,0.0,64.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014816000126302242,0.02844800055027008,0.017008000146597625,0.015696000307798386,0.003941466294662679,0.047807998955249786,0.07356800138950348,0.05626560002565384,0.05626560002565384,0.00842179125412236,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,128,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,False,0.0,128.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.053408000618219376,0.019353600218892097,0.01532800029963255,0.01138302400841626,0.048448000103235245,0.0785600021481514,0.0556256003677845,0.0556256003677845,0.009348274502616908,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,256,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,False,0.0,256.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015039999969303608,0.03139200061559677,0.01823679991066456,0.016159999649971724,0.004860071238302512,0.055424001067876816,0.08505599945783615,0.0640383992344141,0.0640383992344141,0.00921448636178623,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,512,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,False,0.0,512.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.026528000831604004,0.017324799951165915,0.01536000007763505,0.0036004822686428305,0.07660800218582153,0.0942080020904541,0.08209280073642732,0.08209280073642732,0.00515895587669752,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.021247999742627144,0.016403199825435876,0.01532800029963255,0.001995897022647934,0.11395200341939926,0.15113599598407745,0.12431039959192276,0.12431039959192276,0.011164431123683732,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.017184000462293625,0.028672000393271446,0.019865600019693376,0.017823999747633934,0.0035798491315929977,0.3171840012073517,0.3341119885444641,0.3261695951223373,0.3261695951223373,0.005111046452878918,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.024639999493956566,0.030400000512599945,0.02656640000641346,0.02556800004094839,0.0020189846603237303,1.0648640394210815,1.0828479528427124,1.0715327858924866,1.0715327858924866,0.005558639263049851,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014976000413298607,0.021695999428629875,0.017305599898099898,0.01593599934130907,0.0025718046517268054,0.04956800118088722,0.07932800054550171,0.06228480041027069,0.06228480041027069,0.01027160349757827,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,64,448.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,True,448.0,512.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64s512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01539199985563755,0.03580800071358681,0.019686400331556796,0.017136000096797943,0.005918387811304003,0.05158400163054466,0.10713600367307663,0.06364160068333148,0.06364160068333148,0.015832957809696766,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,128,896.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,True,896.0,1024.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015168000012636185,0.02223999984562397,0.016672000009566545,0.015887999907135963,0.0020934945946034563,0.06521599739789963,0.08902399986982346,0.07520959973335266,0.07520959973335266,0.007913840684102929,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,256,1792.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,True,1792.0,2048.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015231999568641186,0.04028800129890442,0.019971200078725816,0.01646399963647127,0.007351305886577286,0.14467200636863708,0.16844800114631653,0.15363519936800005,0.15363519936800005,0.008174435899956223,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,512,3584.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,3584.0,4096.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015519999898970127,0.02304000034928322,0.01775679988786578,0.016784000210464,0.0025077243712082584,0.33740800619125366,0.35343998670578003,0.3445120006799698,0.3445120006799698,0.00445648463590358,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,1024,7168.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,True,7168.0,8192.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1ks8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015647999942302704,0.02393599972128868,0.01809599995613098,0.01654400024563074,0.002998393102466254,0.0,0.0,0.0,0.0,0.0,0.0504320003092289,0.0843840017914772,0.060083200410008426,0.060083200410008426,0.00986959318572296,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01603199914097786,0.030047999694943428,0.019510399922728537,0.017680000513792038,0.004065185265963332,0.0,0.0,0.0,0.0,0.0,0.05004800111055374,0.07036799937486649,0.059315200522542,0.059315200522542,0.006537768821329647,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.02393599972128868,0.018035199772566558,0.016512000001966953,0.0030667689116777724,0.0,0.0,0.0,0.0,0.0,0.05100800096988678,0.06735999882221222,0.058387200161814694,0.058387200161814694,0.005832787739241381,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.026208000257611275,0.017500799987465142,0.01646399963647127,0.0030666103306165714,0.0,0.0,0.0,0.0,0.0,0.05023999884724617,0.07254400104284286,0.057254400476813315,0.057254400476813315,0.006890853653068151,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.027327999472618103,0.0179776000790298,0.01648000068962574,0.003783417447531392,0.0,0.0,0.0,0.0,0.0,0.04819199815392494,0.07100799679756165,0.05621119923889638,0.05621119923889638,0.007824391484124725,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015647999942302704,0.036448001861572266,0.019136000238358975,0.016704000532627106,0.006076530095624803,0.0,0.0,0.0,0.0,0.0,0.047488000243902206,0.08441600203514099,0.0588383998721838,0.0588383998721838,0.011275940726332522,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015135999768972397,0.033952001482248306,0.02119360016658902,0.018000000156462193,0.007136646614305304,0.0,0.0,0.0,0.0,0.0,0.04931199923157692,0.06992000341415405,0.05755840018391609,0.05755840018391609,0.007297587694315226,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.034272000193595886,0.0204415999352932,0.017311999574303627,0.00695404701803013,0.0,0.0,0.0,0.0,0.0,0.05215999856591225,0.0735040009021759,0.06117440015077591,0.06117440015077591,0.007381118436894922,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.03743999823927879,0.02012479966506362,0.01775999926030636,0.006181045509079057,0.0,0.0,0.0,0.0,0.0,0.06355199962854385,0.08508799970149994,0.07019200026988984,0.07019200026988984,0.0062246580442117845,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015552000142633915,0.032607998698949814,0.01959999995306134,0.017487999983131886,0.004882475068460749,0.0,0.0,0.0,0.0,0.0,0.04918399825692177,0.0865280032157898,0.05973760038614274,0.05973760038614274,0.011546847942113974,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015168000012636185,0.02675200067460537,0.017430400010198355,0.016560000367462635,0.003243135094239819,0.0,0.0,0.0,0.0,0.0,0.052671998739242554,0.08367999643087387,0.06238719932734965,0.06238719932734965,0.011207824780630104,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.03612799942493439,0.019327999837696553,0.01688000001013279,0.006058251425153085,0.0,0.0,0.0,0.0,0.0,0.06364800035953522,0.07878399640321732,0.06935679838061332,0.06935679838061332,0.004515588328677643,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.03711999952793121,0.019670399930328132,0.017152000218629837,0.006165994646522264,0.0,0.0,0.0,0.0,0.0,0.09071999788284302,0.11507199704647064,0.10252480059862136,0.10252480059862136,0.008782544051535657,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015039999969303608,0.026528000831604004,0.018396800104528665,0.01601599995046854,0.004279788048986283,0.0,0.0,0.0,0.0,0.0,0.05331199988722801,0.07977599650621414,0.06076480001211167,0.06076480001211167,0.008761579122069606,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.02643200010061264,0.01726400004699826,0.015855999663472176,0.003210008417242029,0.0,0.0,0.0,0.0,0.0,0.062431998550891876,0.08246400207281113,0.06970879957079888,0.06970879957079888,0.007016341676068233,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014911999925971031,0.02223999984562397,0.0166015999391675,0.015887999907135963,0.00204913969129354,0.0,0.0,0.0,0.0,0.0,0.10127999633550644,0.1141119971871376,0.10621120035648347,0.10621120035648347,0.004029318311754605,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.03363199904561043,0.019305599946528675,0.016671999357640743,0.0055445582307981234,0.0,0.0,0.0,0.0,0.0,0.1319040060043335,0.15839999914169312,0.14040640145540234,0.14040640145540234,0.007998041073596942,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014368000440299511,0.04447999969124794,0.018908800091594458,0.0157279996201396,0.0086814937461721,0.0,0.0,0.0,0.0,0.0,0.06428799778223038,0.08982399851083755,0.07349760085344315,0.07349760085344315,0.008605284512197258,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.028672000393271446,0.01890560006722808,0.016080000437796116,0.004797584627815021,0.0,0.0,0.0,0.0,0.0,0.11123199760913849,0.14115199446678162,0.11942399889230729,0.11942399889230729,0.008513394706791027,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.024927999824285507,0.016915200091898442,0.015216000378131866,0.003374147499442635,0.0,0.0,0.0,0.0,0.0,0.15887999534606934,0.18111999332904816,0.16934399753808976,0.16934399753808976,0.007415181260761123,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.026944000273942947,0.017737600207328796,0.015199999790638685,0.00415598714375255,0.0,0.0,0.0,0.0,0.0,0.2192319929599762,0.23472000658512115,0.22809920012950893,0.22809920012950893,0.004730841376327335,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.05052800104022026,0.020320000313222408,0.015520000364631414,0.010604522177924678,0.024270629882498958,0.03340247625954076,0.028446344104128624,0.028446344104128624,0.0032330369099793834,0.023697370291069768,0.03261352722995356,0.027774456325453972,0.027774456325453972,0.0031566742680923386,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,72,,,,,,,,False,,,64,BF16,generic,none,CUDA_EVENT,True,[64],[0],"[512, 512, 512, 512, 512, 512, 512, 512]",1,8,8,9,8,512.0,0.1111111111111111,q64_8q1s512,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.033663999289274216,0.019987199828028678,0.018240000121295452,0.005522929139253732,0.0259194055660947,0.03719755183990719,0.029916029687899703,0.029916029687899703,0.003966666590554318,0.027104595853449518,0.03889844644729374,0.03128396954022015,0.03128396954022015,0.004148046317967881,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,136,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,8,8,9,8,1024.0,0.1111111111111111,q128_8q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014592000283300877,0.03299200162291527,0.019840000104159115,0.016207999549806118,0.006546343008726814,0.02587869595769926,0.03763167265431482,0.030174939058162802,0.030174939058162802,0.0037303581782277364,0.026473304070195713,0.03849632587654989,0.03086826083864964,0.03086826083864964,0.003816069654529222,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,144,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,16,16,17,16,1024.0,0.058823529411764705,q128_16q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.013824000023305416,0.021023999899625778,0.016304000187665223,0.015584000386297703,0.0023236165806545476,0.031810621525966996,0.04156949936878106,0.0346749350032807,0.0346749350032807,0.003130209181143985,0.035677378270900374,0.04662250161636451,0.038889864871740294,0.038889864871740294,0.0035107033960828727,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,272,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,16,16,17,16,2048.0,0.058823529411764705,q256_16q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.02175999991595745,0.01569600012153387,0.015008000191301107,0.0020882666168036863,0.038211712107062853,0.07212229256520057,0.04364509673334097,0.04364509673334097,0.009671953074025085,0.0476442859917874,0.08992570455184198,0.05441890342616107,0.05441890342616107,0.01205947791784038,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,288,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,32,32,33,32,2048.0,0.030303030303030304,q256_32q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014368000440299511,0.033824000507593155,0.017628800217062236,0.014864000026136637,0.005791495403857738,0.05214261250030033,0.06266261508706669,0.05677791295527661,0.05677791295527661,0.0030298223079651514,0.08648138506878382,0.10392938682791132,0.09416928531647478,0.09416928531647478,0.005025126612204489,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,544,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q512_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.031199999153614044,0.017900799959897996,0.015343999955803156,0.004974475661316249,0.06411958891421111,0.07405276123263956,0.06793047918211377,0.06793047918211377,0.0033918658556700006,0.14058441263169497,0.16236323591492058,0.1489399211274489,0.1489399211274489,0.00743678300375353,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,576,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,64,64,65,64,4096.0,0.015384615384615385,q512_64q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.03855999931693077,0.018495999928563833,0.015647999942302704,0.006918530056761627,0.09872985549401277,0.10683454583043753,0.10185316839884552,0.10185316839884552,0.0020802254037042074,0.2743261390166379,0.2968454508984596,0.2830044295482752,0.2830044295482752,0.005780016596065092,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192]",1,64,64,65,64,8192.0,0.015384615384615385,q1k_64q1s8k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.014911999925971031,0.030400000512599945,0.01977920001372695,0.01726400014013052,0.005350883464206169,0.13918872472233365,0.16279522855335207,0.1501912864839173,0.1501912864839173,0.008992185529011513,0.11892328861766266,0.13909276049083735,0.1283239123428725,0.1283239123428725,0.007682951884956939,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q2k_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.01727999933063984,0.02223999984562397,0.01819519978016615,0.017680000513792038,0.0014397298270620873,0.3728044181625443,0.38295504353701676,0.3761264483787333,0.3761264483787333,0.0033660272332490977,0.07967557017401883,0.08184495665371805,0.08038555277807365,0.08038555277807365,0.0007193856241088455,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,16,16,17,16,4096.0,0.058823529411764705,q4k_16q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio +0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.034591998904943466,0.01941439984366298,0.01756799966096878,0.005541380584373771,0.05951999872922897,0.08268799632787704,0.06715519949793816,0.06715519949793816,0.006657802116288364,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,2,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512]",1024,512,512,512.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.03283200040459633,0.019180799927562477,0.016543999314308167,0.0052187911233635975,0.07199999690055847,0.08675199747085571,0.07749439924955369,0.07749439924955369,0.004849874741156772,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,4,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512]",2048,512,512,512.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01724799908697605,0.02284800074994564,0.01928640007972717,0.018400000408291817,0.0020641390157565697,0.09676799923181534,0.12310399860143663,0.10618879944086074,0.10618879944086074,0.008982738207839057,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512]",4096,512,512,512.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.024224000051617622,0.03315199911594391,0.027436799928545953,0.027328000403940678,0.002679154874546328,0.14716799557209015,0.16412800550460815,0.15470399856567385,0.15470399856567385,0.005423454433987419,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512]",8192,512,512,512.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.01833599992096424,0.04806400090456009,0.026252799853682517,0.022672000341117382,0.00878438440429033,0.1844799965620041,0.2072959989309311,0.19359359890222552,0.19359359890222552,0.007663539820967659,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,2,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048]",4096,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median +0.0,0.0,0.0,0.0,0.0,0.024480000138282776,0.04979199916124344,0.029081599973142146,0.025679999962449074,0.007227422044689197,0.34147199988365173,0.37968000769615173,0.3583200007677078,0.3583200007677078,0.011804422100726231,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,4,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048, 2048, 2048]",8192,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median diff --git a/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/attention_true_mixed_fused.csv b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/attention_true_mixed_fused.csv new file mode 100644 index 0000000..153bb52 --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/attention_true_mixed_fused.csv @@ -0,0 +1,31 @@ +num_tensor_parallel_workers,batch_spec,num_prefill_seqs,num_decode_seqs,total_prefill_tokens,total_decode_tokens,decode_avg_kv_cache_size,attention_core_mean_ms,attention_core_mean_as_median_ms,kv_cache_update_median_ms,pure_prefill_reference_mean_ms,pure_decode_reference_mean_ms,projected_prefill_mean_ms,projected_decode_mean_ms,projection_sum_error_ms,representation +1,q64_8q1s512,1,8,64,8,512.0,0.06604800000786781,0.06604800000786781,0.021359999664127827,0.05810240097343922,0.0600041144660541,0.032492258074592426,0.03355574193327539,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q128_8q1s1k,1,8,128,8,1024.0,0.07483199909329416,0.07483199909329416,0.024255999363958836,0.05587520003318787,0.06090559959411622,0.03580428402241854,0.03902771507087562,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q128_16q1s1k,1,16,128,16,1024.0,0.10597119852900506,0.10597119852900506,0.018112000077962875,0.05587520003318787,0.06891520097851753,0.04744885718421094,0.05852234134479412,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q256_16q1s2k,1,16,256,16,2048.0,0.13697599917650224,0.13697599917650224,0.01673599984496832,0.056396800279617305,0.11392960175871848,0.04535414343408448,0.09162185574241775,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q256_32q1s2k,1,32,256,32,2048.0,0.2163648009300232,0.2163648009300232,0.01515199989080429,0.056396800279617305,0.13807999789714814,0.06274415549817247,0.15362064543185072,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q512_32q1s4k,1,32,512,32,4096.0,0.3746495962142944,0.3746495962142944,0.016191999427974224,0.07432000041007995,0.2231455981731415,0.09360396051475776,0.2810456356995366,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q512_64q1s4k,1,64,512,64,4096.0,0.6718560099601746,0.6718560099601746,0.024848000146448612,0.07432000041007995,0.4058080047369003,0.10399797220840973,0.5678580377517648,-1.1102230246251565e-16,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q1k_64q1s8k,1,64,1024,64,8192.0,1.3472000002861022,1.3472000002861022,0.019600000232458115,0.1307712011039257,0.7464000046253203,0.2008444429250931,1.1463555573610091,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q2k_32q1s4k,1,32,2048,32,4096.0,0.6351647913455962,0.6351647913455962,0.028256000019609928,0.33396480381488797,0.2231455981731415,0.38075520430942184,0.25440958703617433,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +1,q4k_16q1s4k,1,16,4096,16,4096.0,1.2515872120857237,1.2515872120857237,0.04395199939608574,1.0999775886535645,0.1389280006289482,1.1112371236754128,0.14035008841031085,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q64_8q1s512,1,8,64,8,512.0,0.05652800053358078,0.05652800053358078,0.019600000232458115,0.05961279980838299,0.055968457407185014,0.029155180178492036,0.027372820355088746,6.938893903907228e-18,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q128_8q1s1k,1,8,128,8,1024.0,0.07362559959292413,0.07362559959292413,0.014431999996304512,0.05882879942655563,0.05778240002691746,0.03714313592014963,0.036482463672774496,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q128_16q1s1k,1,16,128,16,1024.0,0.0736224003136158,0.0736224003136158,0.014479999896138906,0.05882879942655563,0.06270079985260964,0.03563837490653034,0.037984025407085474,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q256_16q1s2k,1,16,256,16,2048.0,0.10047360062599181,0.10047360062599181,0.01425600005313754,0.05459520071744919,0.06628479920327664,0.045378692890289625,0.05509490773570219,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q256_32q1s2k,1,32,256,32,2048.0,0.14032640159130094,0.14032640159130094,0.01566399959847331,0.05459520071744919,0.09493440166115762,0.05123499252968345,0.0890914090616175,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q512_32q1s4k,1,32,512,32,4096.0,0.22105600088834762,0.22105600088834762,0.016032000072300434,0.06650560013949873,0.13783999979496003,0.07194410845270183,0.14911189243564577,-2.7755575615628914e-17,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q512_64q1s4k,1,64,512,64,4096.0,0.36867519915103913,0.36867519915103913,0.015263999812304974,0.06650560013949873,0.22715839892625808,0.0834932625520734,0.2851819365989658,5.551115123125783e-17,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q1k_64q1s8k,1,64,1024,64,8192.0,0.6853824079036711,0.6853824079036711,0.015856000129133463,0.08607039973139763,0.40332479774951924,0.12053885718696096,0.5648435507167102,1.1102230246251565e-16,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q2k_32q1s4k,1,32,2048,32,4096.0,0.3503839999437332,0.3503839999437332,0.018432000651955605,0.19546559900045393,0.13783999979496003,0.2054811520619412,0.14490284788179197,-5.551115123125783e-17,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +2,q4k_16q1s4k,1,16,4096,16,4096.0,0.7185311973094941,0.7185311973094941,0.026575999334454536,0.5800191938877105,0.10921279862523078,0.6046757700946376,0.11385542721485654,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q64_8q1s512,1,8,64,8,512.0,0.0562208004295826,0.0562208004295826,0.015520000364631414,0.06054079942405224,0.0591108573866742,0.028446344104128624,0.027774456325453972,-6.938893903907228e-18,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q128_8q1s1k,1,8,128,8,1024.0,0.061199999228119854,0.061199999228119854,0.018240000121295452,0.05626560002565384,0.0588383998721838,0.029916029687899703,0.03128396954022015,-6.938893903907228e-18,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q128_16q1s1k,1,16,128,16,1024.0,0.06104319989681244,0.06104319989681244,0.016207999549806118,0.05626560002565384,0.05755840018391609,0.030174939058162802,0.03086826083864964,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q256_16q1s2k,1,16,256,16,2048.0,0.07356479987502099,0.07356479987502099,0.015584000386297703,0.0556256003677845,0.06238719932734965,0.0346749350032807,0.038889864871740294,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q256_32q1s2k,1,32,256,32,2048.0,0.09806400015950203,0.09806400015950203,0.015008000191301107,0.0556256003677845,0.06935679838061332,0.04364509673334097,0.05441890342616107,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q512_32q1s4k,1,32,512,32,4096.0,0.1509471982717514,0.1509471982717514,0.014864000026136637,0.0640383992344141,0.10621120035648347,0.05677791295527661,0.09416928531647478,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q512_64q1s4k,1,64,512,64,4096.0,0.21687040030956264,0.21687040030956264,0.015343999955803156,0.0640383992344141,0.14040640145540234,0.06793047918211377,0.1489399211274489,2.7755575615628914e-17,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q1k_64q1s8k,1,64,1024,64,8192.0,0.3848575979471207,0.3848575979471207,0.015647999942302704,0.08209280073642732,0.22809920012950893,0.10185316839884552,0.2830044295482752,0.0,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q2k_32q1s4k,1,32,2048,32,4096.0,0.2785151988267898,0.2785151988267898,0.01726400014013052,0.12431039959192276,0.10621120035648347,0.1501912864839173,0.1283239123428725,-5.551115123125783e-17,one_fused_FA3_call_projected_for_Frontier_with_total_conservation +4,q4k_16q1s4k,1,16,4096,16,4096.0,0.456512001156807,0.456512001156807,0.017680000513792038,0.3261695951223373,0.06970879957079888,0.3761264483787333,0.08038555277807365,-5.551115123125783e-17,one_fused_FA3_call_projected_for_Frontier_with_total_conservation diff --git a/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/linear_op.csv b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/linear_op.csv new file mode 100644 index 0000000..2803f02 --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/linear_op.csv @@ -0,0 +1,37 @@ +time_stats.emb.min,time_stats.emb.max,time_stats.emb.mean,time_stats.emb.median,time_stats.emb.std,time_stats.input_layernorm.min,time_stats.input_layernorm.max,time_stats.input_layernorm.mean,time_stats.input_layernorm.median,time_stats.input_layernorm.std,time_stats.attn_pre_proj.min,time_stats.attn_pre_proj.max,time_stats.attn_pre_proj.mean,time_stats.attn_pre_proj.median,time_stats.attn_pre_proj.std,time_stats.attn_rope.min,time_stats.attn_rope.max,time_stats.attn_rope.mean,time_stats.attn_rope.median,time_stats.attn_rope.std,time_stats.attn_post_proj.min,time_stats.attn_post_proj.max,time_stats.attn_post_proj.mean,time_stats.attn_post_proj.median,time_stats.attn_post_proj.std,time_stats.post_attention_layernorm.min,time_stats.post_attention_layernorm.max,time_stats.post_attention_layernorm.mean,time_stats.post_attention_layernorm.median,time_stats.post_attention_layernorm.std,n_head,n_kv_head,n_embd,n_expanded_embd,vocab_size,use_gated_mlp,use_qk_norm,attn_output_gate,num_tokens,num_tensor_parallel_workers,padded_n_embd,padded_n_expanded_embd,model_arch,is_step2_mini,share_expert_dim,share_q_dim,measurement_type,profiling_precision,quant_signature +0.029184000566601753,0.06780800223350525,0.03157280012965202,0.030736000277101994,0.005874173435341216,0.033215999603271484,0.04825599864125252,0.03443359974771738,0.0337119996547699,0.0031825678429048183,1.438431978225708,1.505568027496338,1.446228802204132,1.4429279565811157,0.014128607642643025,0.538752019405365,0.5440319776535034,0.5416463971138,0.5420799851417542,0.0016099306164432847,1.0073280334472656,1.0163840055465698,1.0098415970802308,1.0081279873847961,0.0032980457197329728,0.04022400081157684,0.041728001087903976,0.04091359991580248,0.04081599973142147,0.0004728505416767937,32,4,2048,768,151936,True,True,False,8192,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.01360000018030405,0.06784000247716904,0.017755200061947106,0.0179840000346303,0.00837681421401443,0.01836800016462803,0.03651199862360954,0.019606399815529585,0.018719999119639397,0.0038821958848767424,0.7512000203132629,0.8208960294723511,0.7566704005002975,0.75382399559021,0.014793092586577971,0.28995200991630554,0.29337599873542786,0.29135999977588656,0.29150401055812836,0.000998381071258815,0.5149760246276855,0.5169600248336792,0.5160208016633987,0.5158880054950714,0.0005038652783291977,0.02051199972629547,0.021503999829292297,0.021067200042307378,0.021104000508785248,0.00023542855306902367,32,4,2048,768,151936,True,True,False,4096,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.0080960001796484,0.04281599819660187,0.011092799971811474,0.011039999779313803,0.005489135752949302,0.012223999947309494,0.026335999369621277,0.013187199970707298,0.01247999956831336,0.0030236510562153375,0.3928639888763428,0.45372799038887024,0.3976895987987518,0.39528000354766846,0.012905176716136006,0.1547199934720993,0.15884800255298615,0.15712319910526276,0.1573439985513687,0.001165121945135037,0.26633599400520325,0.268095999956131,0.26719200164079665,0.2671840041875839,0.0004242740199415328,0.013024000450968742,0.013887999579310417,0.013489600038155913,0.013520000036805868,0.0002382817554057738,32,4,2048,768,151936,True,True,False,2048,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.00825599953532219,0.04755200073122978,0.02398160002194345,0.01961600035429001,0.00874683840888523,0.018880000337958336,0.03868800029158592,0.021590400114655496,0.0208320003002882,0.004057015751746236,0.24316799640655518,0.2710399925708771,0.2521967992186546,0.25065599381923676,0.007998418528894075,0.09644799679517746,0.19120000302791595,0.10407840013504029,0.09963199868798256,0.020043722414992166,0.13600000739097595,0.18892799317836761,0.15760480016469955,0.15760000050067902,0.0112223677907762,0.009664000011980534,0.010015999898314476,0.009836799977347255,0.009824000298976898,9.016971952948177e-05,32,4,2048,768,151936,True,True,False,1024,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.017376000061631203,0.044704001396894455,0.026318399980664254,0.027312000282108784,0.007565344034680866,0.01836800016462803,0.03014400042593479,0.021276800055056812,0.020655999891459942,0.002632977855097951,0.1438719928264618,0.17132799327373505,0.152497598528862,0.15012799948453903,0.007947150319625347,0.1430719941854477,0.19305600225925446,0.16630879789590836,0.1685439944267273,0.014628024163894684,0.08899199962615967,0.10467199981212616,0.0943599995225668,0.09374399855732918,0.003472669494074113,0.007615999784320593,0.007935999892652035,0.007769599952735007,0.0077760000713169575,7.680004540222077e-05,32,4,2048,768,151936,True,True,False,512,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.016992000862956047,0.0544000007212162,0.02573199989274144,0.026016000658273697,0.00803323401720434,0.018432000651955605,0.02348800003528595,0.020648000109940768,0.02062400057911873,0.0013939985047930988,0.10220800340175629,0.1361600011587143,0.11850560046732425,0.11684799939393997,0.010637754898360304,0.16710400581359863,0.21110400557518005,0.19078560024499894,0.19409599900245667,0.013714352646558832,0.06265600025653839,0.0740479975938797,0.06842879951000214,0.0690080001950264,0.0031292240446560557,0.00979200005531311,0.033440001308918,0.01864320016466081,0.017280000261962414,0.006957998188876383,32,4,2048,768,151936,True,True,False,256,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.017152000218629837,0.04396799951791763,0.025907999789342284,0.02598400041460991,0.007714554737915267,0.018400000408291817,0.03667199984192848,0.024132800102233887,0.02112000063061714,0.006120348733354326,0.10678400099277496,0.1363839954137802,0.1193264003843069,0.11583999916911125,0.009838647443214228,0.17017599940299988,0.22748799622058868,0.18853759989142418,0.18433599919080734,0.015728078443174653,0.04569600149989128,0.06652799993753433,0.05192639995366335,0.05151999928057194,0.004516605694976449,0.021856000646948814,0.026335999369621277,0.02384479995816946,0.023599999956786633,0.0011301153013314744,32,4,2048,768,151936,True,True,False,128,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.017343999817967415,1.0683200359344482,0.05748240072280168,0.029504000209271908,0.16366824814254827,0.018688000738620758,0.3317759931087494,0.03685439983382821,0.021151999942958355,0.06767422466731164,0.10255999863147736,0.9434880018234253,0.16412640027701855,0.11956800147891045,0.17964606281728834,0.1714559942483902,2.1306240558624268,0.3011296011507511,0.1926399990916252,0.42310127734378766,0.03574400022625923,0.6859520077705383,0.08389280084520578,0.04279999993741512,0.14321647071615612,0.020479999482631683,0.1831360012292862,0.033024000097066165,0.023856000043451786,0.03470987082429836,32,4,2048,768,151936,True,True,False,64,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.016095999628305435,0.05142400041222572,0.026363200135529043,0.02676799986511469,0.008637725852473854,0.01849599927663803,0.03577600046992302,0.022193600237369538,0.020848000422120094,0.004615266181181815,0.10540799796581268,0.15014399588108063,0.12211520001292228,0.11896000057458878,0.012772013396624768,0.17315199971199036,0.21478399634361267,0.1881632000207901,0.1873439997434616,0.011761164657572015,0.03481600061058998,0.058079998940229416,0.042200000025331974,0.03969600051641464,0.006461281521769989,0.02143999934196472,0.038816001266241074,0.02466559996828437,0.023856000043451786,0.0035418033748569927,32,4,2048,768,151936,True,True,False,32,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.015904000028967857,0.03753599897027016,0.023127999808639287,0.02527999971061945,0.0054230027890305385,0.018400000408291817,0.03001599945127964,0.020488000102341176,0.020096000283956528,0.002585688394137697,0.10355199873447418,0.1438400000333786,0.11536479964852334,0.11124800145626068,0.011136028294919255,0.16502399742603302,0.2072959989309311,0.18646399974822997,0.19075199961662292,0.013296437761247597,0.03142400085926056,0.05215999856591225,0.03888959977775812,0.03750399872660637,0.0057399302067536314,0.020128000527620316,0.04064000025391579,0.023937600292265417,0.023648000322282314,0.004144197400898248,32,4,2048,768,151936,True,True,False,16,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.015200000256299973,0.037151999771595,0.02144480012357235,0.02195199951529503,0.005576364091933697,0.017952000722289085,0.0226879995316267,0.019934400077909233,0.019952000118792057,0.0011812499470458758,0.10063999891281128,0.13468800485134125,0.11595199964940547,0.1207519993185997,0.011974301621092394,0.16332800686359406,0.20748800039291382,0.18162400051951408,0.1767839938402176,0.01474120743720334,0.03222399950027466,0.043455999344587326,0.03829439990222454,0.03859200142323971,0.0031378131240041122,0.020959999412298203,0.03587200120091438,0.023795200139284135,0.023423999547958374,0.0031339489695198443,32,4,2048,768,151936,True,True,False,8,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +0.014944000169634819,0.04022400081157684,0.02162720002233982,0.022463999688625336,0.006017219317026815,0.018464000895619392,0.026528000831604004,0.021264000236988066,0.020896000787615776,0.001934095017586082,0.10156799852848053,0.1703999936580658,0.12565439902245998,0.1244799979031086,0.01641776722785409,0.1653759926557541,0.23865599930286407,0.1969360001385212,0.19223999977111816,0.02058903050274278,0.03254399821162224,0.06752000004053116,0.0443536002188921,0.041519999504089355,0.00984829071098989,0.020096000283956528,0.040031999349594116,0.026934400014579297,0.02478400059044361,0.00562071702648593,32,4,2048,768,151936,True,True,False,1,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.7531200051307678,0.8461440205574036,0.7618160009384155,0.7576479911804199,0.019464233617982506,0.2922559976577759,0.2985599935054779,0.2953856036067009,0.29576000571250916,0.001575901077689139,0.510047972202301,0.5140479803085327,0.5121696025133133,0.5123839974403381,0.0012263137313476844,,,,,,32,4,2048,768,151936,True,True,False,8192,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.39529600739479065,0.47279998660087585,0.40216960161924364,0.39825600385665894,0.0162749796240819,0.15625600516796112,0.16211199760437012,0.15959519892930984,0.15988799929618835,0.0011493418942396922,0.2635200023651123,0.2642880082130432,0.2639120012521744,0.26392000913619995,0.0001903593401384135,,,,,,32,4,2048,768,151936,True,True,False,4096,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.2531839907169342,0.32419198751449585,0.26924319565296173,0.26049599051475525,0.01657194262368116,0.10051199793815613,0.2375359982252121,0.12411200068891048,0.10311999917030334,0.039466165428540506,0.15881599485874176,0.19289599359035492,0.16896959990262986,0.1640480011701584,0.009162416086418127,,,,,,32,4,2048,768,151936,True,True,False,2048,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.15302400290966034,0.1780800074338913,0.16284480094909667,0.16113600134849548,0.00740355661356144,0.14521600306034088,0.20233599841594696,0.17807039842009545,0.1796799972653389,0.013908448560094403,0.0907519981265068,0.09750399738550186,0.09460479989647866,0.09478399902582169,0.0017965487667361475,,,,,,32,4,2048,768,151936,True,True,False,1024,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11740799993276596,0.17958399653434753,0.13262080028653145,0.12878400087356567,0.014146060532423056,0.17468799650669098,0.21161599457263947,0.1910431995987892,0.18966399878263474,0.01270903647700971,0.05926400050520897,0.07577600330114365,0.06530559975653887,0.06404799968004227,0.00479458462514625,,,,,,32,4,2048,768,151936,True,True,False,512,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11260800063610077,0.17209599912166595,0.13610880002379416,0.13809599727392197,0.017675922458993677,0.18729600310325623,0.26822400093078613,0.20815680101513861,0.2078079953789711,0.01700718593658771,0.04499199986457825,0.06537599861621857,0.0507551996037364,0.04787199944257736,0.005727123232692158,,,,,,32,4,2048,768,151936,True,True,False,256,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11257600039243698,0.23452800512313843,0.13866880126297473,0.13964799791574478,0.026590047697062115,0.1828799992799759,0.24751999974250793,0.20735519900918006,0.20670399814844131,0.01500438131586336,0.03654399886727333,0.05593600124120712,0.0408239996060729,0.03892800025641918,0.004864409450710354,,,,,,32,4,2048,768,151936,True,True,False,128,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11734399944543839,0.18726399540901184,0.13890240006148816,0.13308800011873245,0.019086167340006257,0.16991999745368958,0.2443840056657791,0.19185120090842248,0.19257599860429764,0.018017536159219673,0.03033600002527237,0.04956800118088722,0.038387199863791466,0.03750400058925152,0.00500897018702887,,,,,,32,4,2048,768,151936,True,True,False,64,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11420799791812897,0.18115200102329254,0.13938880078494548,0.1393439993262291,0.018141313962922536,0.1693439930677414,0.221343994140625,0.19187839925289155,0.19438399374485016,0.01430752121272052,0.03017600066959858,0.06019200012087822,0.03866560012102127,0.0364960003644228,0.0074199790031205266,,,,,,32,4,2048,768,151936,True,True,False,32,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11276800185441971,0.16223999857902527,0.1331360016018152,0.13305599987506866,0.01432493740801146,0.17187200486660004,0.23625600337982178,0.19287680014967917,0.1913280040025711,0.01754628831589704,0.029823999851942062,0.07574400305747986,0.03900959976017475,0.036927999928593636,0.009277465083962879,,,,,,32,4,2048,768,151936,True,True,False,16,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.1130559965968132,0.19814400374889374,0.13379519879817964,0.12531199678778648,0.020074427302248836,0.16841599345207214,0.21139200031757355,0.1893615983426571,0.19092799723148346,0.012418720676762711,0.029503999277949333,0.07558400183916092,0.040144000016152856,0.03728000074625015,0.010223239196498205,,,,,,32,4,2048,768,151936,True,True,False,8,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.115167997777462,0.2640640139579773,0.13805920109152794,0.13118399679660797,0.03132849683515479,0.17103999853134155,0.2977280020713806,0.19899839907884598,0.1976960003376007,0.028928046763067948,0.0297279991209507,0.05990400165319443,0.03834720011800528,0.0363520011305809,0.0070885330713495905,,,,,,32,4,2048,768,151936,True,True,False,1,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.3940800130367279,0.46483200788497925,0.39923040121793746,0.3957759886980057,0.015108903906233569,0.16022400557994843,0.1634880006313324,0.16203359961509706,0.16228799521923065,0.0010220720912414007,0.26073598861694336,0.2627840042114258,0.26138080209493636,0.2613760083913803,0.00041640363494172775,,,,,,32,4,2048,768,151936,True,True,False,8192,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.2536959946155548,0.27161601185798645,0.25960480123758317,0.2577280104160309,0.005142017404245015,0.09849599748849869,0.10281600058078766,0.10057279989123344,0.10063999891281128,0.0008836232237268523,0.13913600146770477,0.17606399953365326,0.15875840038061143,0.15988799929618835,0.010058952112389172,,,,,,32,4,2048,768,151936,True,True,False,4096,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.15142400562763214,0.1780479997396469,0.16139679849147798,0.1602879986166954,0.0070656055731385115,0.14601600170135498,0.23343999683856964,0.17913119941949845,0.179967999458313,0.023065274309176566,0.09388799965381622,0.12108799815177917,0.10317599996924401,0.10073599964380264,0.007364345618470178,,,,,,32,4,2048,768,151936,True,True,False,2048,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.12198399752378464,0.18406400084495544,0.13770400024950505,0.13232000172138214,0.01623164885687898,0.1773120015859604,0.20688000321388245,0.1870912007987499,0.18535999953746796,0.00825628058448234,0.05766399949789047,0.06739199906587601,0.06187200043350458,0.061216000467538834,0.003004312467037863,,,,,,32,4,2048,768,151936,True,True,False,1024,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11737599968910217,0.18614399433135986,0.13109439946711063,0.12771200388669968,0.01372168725934724,0.17587199807167053,0.2699519991874695,0.19926720038056372,0.19075199961662292,0.02327478982490538,0.041728001087903976,0.06224000081419945,0.05000480003654957,0.049375999718904495,0.006185850944273961,,,,,,32,4,2048,768,151936,True,True,False,512,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.1159679964184761,0.1610880047082901,0.12988320142030715,0.12494400516152382,0.011865375783184065,0.1767680048942566,0.27379199862480164,0.21035519987344742,0.21275199949741364,0.023206964017550125,0.037087999284267426,0.062144000083208084,0.04439679980278015,0.04283200018107891,0.006155226392511492,,,,,,32,4,2048,768,151936,True,True,False,256,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.12015999853610992,0.158720001578331,0.13573280088603495,0.1343199983239174,0.010666830836014414,0.1737920045852661,0.22127999365329742,0.20261440128087999,0.20321600139141083,0.011153965849067301,0.03587200120091438,0.04944000020623207,0.038265600241720675,0.037328001111745834,0.0030431580113575636,,,,,,32,4,2048,768,151936,True,True,False,128,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.1212799996137619,0.15139199793338776,0.13183839991688728,0.13014400005340576,0.00851207547022104,0.17257599532604218,0.2250880002975464,0.1872655987739563,0.18193599581718445,0.013638284975248818,0.02969600073993206,0.0525440014898777,0.03840640028938651,0.03444799967110157,0.007598511754254174,,,,,,32,4,2048,768,151936,True,True,False,64,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11270400136709213,0.1624639928340912,0.13508000001311302,0.13180799782276154,0.014243564451606775,0.17052799463272095,0.23715199530124664,0.1953311987221241,0.1966560035943985,0.01500670718978398,0.030239999294281006,0.05270399898290634,0.03807039987295866,0.03742399998009205,0.004906165602021684,,,,,,32,4,2048,768,151936,True,True,False,32,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.12319999933242798,0.17919999361038208,0.14059039913117885,0.14156799763441086,0.016217662982107223,0.1701119989156723,0.21987199783325195,0.18903039917349815,0.1870879977941513,0.014117854507841239,0.030368000268936157,0.06406400352716446,0.04045119984075427,0.03710399940609932,0.00878942205983628,,,,,,32,4,2048,768,151936,True,True,False,16,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11296000331640244,0.16761599481105804,0.13843199908733367,0.13814399391412735,0.014925286935582404,0.1711679995059967,0.21561600267887115,0.1906527981162071,0.1876479983329773,0.011803992622137974,0.0306560005992651,0.09216000139713287,0.041129599791020155,0.036847999319434166,0.013739721468154687,,,,,,32,4,2048,768,151936,True,True,False,8,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none +,,,,,,,,,,0.11929599940776825,0.2008959949016571,0.14535359852015972,0.13971199840307236,0.024769473061576282,0.16803200542926788,0.25123199820518494,0.19573760256171227,0.19366399943828583,0.023196011081705884,0.03049599938094616,0.08089599758386612,0.04739360017701984,0.0453919991850853,0.01286389846889463,,,,,,32,4,2048,768,151936,True,True,False,1,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none diff --git a/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/manifest.json b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/manifest.json new file mode 100644 index 0000000..eff69e5 --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/manifest.json @@ -0,0 +1,57 @@ +{ + "attention_tp_coverage": [ + 1, + 2, + 4 + ], + "environment_contract": { + "dtype": "bfloat16", + "frontier_commit": "d9cfeb6d8791fbf2f295dd9744c56a666171776e", + "hardware": "NVIDIA H20", + "model": "Qwen3-30B-A3B", + "tensor_parallel_sizes": [ + 1, + 2, + 4 + ], + "vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1", + "vllm_version": "0.20.0" + }, + "inputs": { + "/home/gahow/phd/aituner/runs/frontier-fidelity-envelope-v1/fleet-artifacts/qwen30-attention-composition-tp1-20260717-v1-20260717T014550833983Z/artifacts/artifacts/attention-composition-tp1-v1/raw/flashattn-composition-tp1.json": "ce461be92a5059e2d168b2cbf21b55d9a55ee71c3b0586a3e63cd8288938168d", + "/home/gahow/phd/aituner/runs/frontier-fidelity-envelope-v1/fleet-artifacts/qwen30-attention-composition-tp2-20260717-v1-20260717T014551831545Z/artifacts/artifacts/attention-composition-tp2-v1/raw/flashattn-composition-tp2.json": "997d67fb3a28b488c3aa4945ae7c6d4ecf8a08726ee3cb4652d16c221ff395ad", + "/home/gahow/phd/aituner/runs/frontier-fidelity-envelope-v1/fleet-artifacts/qwen30-attention-composition-tp4-20260717-v1-20260717T014552897206Z/artifacts/artifacts/attention-composition-tp4-v1/raw/flashattn-composition-tp4.json": "046cffd4c11d8a36513167ec25d3e1ca016324715679ea688a58d4a71dfe62b2", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-allreduce-full-tp2-20260716-v1-dispatch-aware-20260716T140743025781Z/artifacts/artifacts/allreduce-full-tp2-v1/raw/allreduce-tp2.json": "97c3c76b5a04e95bd9192423c2b891667c668f39cc0dfecbd097d749939f2d0a", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-allreduce-full-tp4-20260716-v1-dispatch-aware-20260716T141106009788Z/artifacts/artifacts/allreduce-full-tp4-v1/raw/allreduce-tp4.json": "809df9baa6f468cf12bf0c99827475acc67894dd9f3f948976590b665fac0e76", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-flashattn-kv-full-tp1-20260716-v2-20260716T135132587012Z/artifacts/artifacts/flashattn-kv-full-v2-tp1/raw/flashattn-tp1.json": "dcb4c1bf7e76b9c765f78ddd2b8a734f2d7ba2adac13ce017689a8a77fe69a27", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-flashattn-kv-full-tp2-20260716-v2-20260716T135134194295Z/artifacts/artifacts/flashattn-kv-full-v2-tp2/raw/flashattn-tp2.json": "43ce042556ba887c8860614b43ccf0f564e5cebc1a0cffbce299d0acb9fa8d07", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-flashattn-kv-full-tp4-20260716-v2-20260716T135135197200Z/artifacts/artifacts/flashattn-kv-full-v2-tp4/raw/flashattn-tp4.json": "84eef31bcad0f556907a093318a420959d14fdc94474823d11f659704bdfec73", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-frontier-linear-full-20260716-v2-max-tokens-20260716T144444676943Z/artifacts/artifacts/frontier-linear-full-v2/profiles/compute/h20/qwen3-a3b-30b-moe/linear_op.csv": "67666cb0a4901b74599d468df2e31bcaa2a11a7842cc0cefba24ffce62508e0c", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-moe-full-20260716-v1-local-shard-20260716T141334565164Z/artifacts/artifacts/moe-full-v1/raw/moe-full.json": "588f6ad0d69c9636d1b852e3df0a12d13cfe731f050ea7ec7aea457cceefbde8", + "/home/gahow/phd/aituner/runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts/qwen30-vllm020-router-full-20260716-v3-tp-context-20260716T145446098505Z/artifacts/artifacts/router-full-v3/raw/router.json": "1962972e983bff3e06a721ef4ae4ec65728ff669681497a4a7e7f769b88b4931" + }, + "outputs": { + "allreduce.json": "b38d14f990578d668523d25b107aceed433da5020d8ada3b6e44d3562261a3b3", + "attention.csv": "8af0206ffe8f515c124194ecb589a0b8d640c40f59b131dc65c1fe1ad221c007", + "attention_true_mixed_fused.csv": "43ef4be90bddc9aeac6dbbe339feec24162cd1f2129a08fbd959e6ee4eaf5f60", + "linear_op.csv": "67666cb0a4901b74599d468df2e31bcaa2a11a7842cc0cefba24ffce62508e0c", + "moe.csv": "0e4dcba72918a1c4cf4e96ced31ee3829248a19ad54553cebef14417725808b0" + }, + "profile_id": "qwen3-30b-a3b-bf16-vllm020-h20-tp1-2-4-fused-mixed-total-conserving-pure-prefill-batch-composition", + "projection_contract": { + "allreduce": "Frozen exact runtime measurements; base profile-only comparison keeps the historical Frontier CC backend fixed to isolate compute profile fidelity", + "attention": "Pure prefill/extend/decode FA3 core plus separately measured KV update; input/output reshape assumed zero; exported mean is used as median target; true mixed rows use a total-conserving compatibility projection", + "attention_pure_prefill_batch_composition": "Direct FA3 measurements for 2/4 requests at query length 2048 and 2/4/8/16 requests at query length 512 for each TP; included only when batch-composition attention inputs are supplied", + "attention_true_mixed": "The directly measured fused total is preserved in diagnostics. Frontier's two targets are projected by the same-TP pure prefill/decode reference ratio, with projected prefill + decode exactly equal to the fused total; the split is a schema compatibility attribution, not an observation", + "linear": "Frontier profiler using vLLM 0.20 CUDA operators", + "moe": "Replicated gate and fused top-k plus TP-local modular expert kernel; expert measurement already includes prepare/finalize so shuffling is zero" + }, + "row_counts": { + "allreduce": 24, + "attention_frontier_compatible": 150, + "attention_true_mixed_fused_diagnostic": 30, + "linear": 36, + "moe": 72 + }, + "schema_version": "frontier_qwen30_vllm020_frozen_profile.v3" +} diff --git a/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/moe.csv b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/moe.csv new file mode 100644 index 0000000..e5bf507 --- /dev/null +++ b/runs/frontier-fidelity-envelope-v1/profiles/profile-v3-batch-final/moe.csv @@ -0,0 +1,73 @@ +time_stats.moe_gating_linear.min,time_stats.moe_gating_linear.max,time_stats.moe_gating_linear.mean,time_stats.moe_gating_linear.median,time_stats.moe_gating_linear.std,time_stats.moe_gating_routing_topk.min,time_stats.moe_gating_routing_topk.max,time_stats.moe_gating_routing_topk.mean,time_stats.moe_gating_routing_topk.median,time_stats.moe_gating_routing_topk.std,time_stats.moe_shuffling.min,time_stats.moe_shuffling.max,time_stats.moe_shuffling.mean,time_stats.moe_shuffling.median,time_stats.moe_shuffling.std,time_stats.moe_grouped_gemm.min,time_stats.moe_grouped_gemm.max,time_stats.moe_grouped_gemm.mean,time_stats.moe_grouped_gemm.median,time_stats.moe_grouped_gemm.std,num_tokens,num_experts,num_experts_per_device,expert_parallel_size,routing_runtime_path,routing_assignment_policy,routing_weight_policy,routing_uses_router_logits,gating_runtime_context,gating_runtime_context_impl,router_topk,hidden_dim,expert_hidden_dim,use_gated,num_tensor_parallel_workers,total_routed_tokens,model_expansion_ratio,tokens_per_expert_avg,tokens_to_experts_ratio,expert_utilization,min_load_ratio,load_imbalance_cv,max_load_ratio,load_entropy,load_gini_coefficient,load_distribution,seed,moe_grouped_gemm_backend,measurement_type,profiling_precision,model_arch,quant_signature,router_median_nonadditivity_ratio,projection_policy +0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.33926400542259216,0.405023992061615,0.36780479848384856,0.36507199704647064,0.01690507644474779,1,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,1.1943039894104004,1.286784052848816,1.228384006023407,1.2273280024528503,0.02832547242381263,8,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,64,0.375,0.5,0.5,0.3984375,0.0,1.346291201783626,4.0,5.59375,0.661865234375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,1.679744005203247,1.766144037246704,1.7095808148384095,1.7015680074691772,0.02438921262998535,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,128,0.375,1.0,1.0,0.625,0.0,1.015504800579495,5.0,6.15516433212955,0.529052734375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,2.1576640605926514,2.2921600341796875,2.2097824096679686,2.188944101333618,0.045572321842012986,32,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,256,0.375,2.0,2.0,0.875,0.0,0.6343057228182637,2.5,6.64370748444639,0.35369873046875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,2.422368049621582,2.5130879878997803,2.4516672134399413,2.434159994125366,0.03278900287381846,64,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,512,0.375,4.0,4.0,0.984375,0.0,0.4921254921257382,2.25,6.817190042344769,0.272369384765625,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,2.2217600345611572,2.289599895477295,2.2571327924728393,2.263375997543335,0.021660416089449488,128,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,1024,0.375,8.0,8.0,1.0,0.125,0.3486861500690843,1.875,6.908192310183997,0.197662353515625,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,2.18668794631958,2.318079948425293,2.2218016147613526,2.211087942123413,0.035380897213135316,256,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,2048,0.375,16.0,16.0,1.0,0.4375,0.2525504668006971,1.875,6.953347743053017,0.1410369873046875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,2.2291839122772217,2.3929600715637207,2.2908096313476562,2.2804640531539917,0.04479348924786221,512,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,4096,0.375,32.0,32.0,1.0,0.65625,0.15765965680164504,1.5625,6.98229848728205,0.08779525756835938,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,2.0678720474243164,2.1297600269317627,2.0837119817733765,2.0779199600219727,0.017880044357986735,1024,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8192,0.375,64.0,64.0,1.0,0.625,0.12169081635504074,1.3125,6.9892029662356325,0.06879425048828125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,2.916032075881958,3.0819520950317383,2.9805248022079467,2.9656319618225098,0.05482195799019572,2048,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,16384,0.375,128.0,128.0,1.0,0.796875,0.07935434147688751,1.1796875,6.9954297964750305,0.044734954833984375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,4.421599864959717,4.535359859466553,4.486294317245483,4.497056007385254,0.036990243787549344,4096,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,32768,0.375,256.0,256.0,1.0,0.8203125,0.060849326483103046,1.17578125,6.9973188375859685,0.033740997314453125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,7.302591800689697,7.402751922607422,7.354758310317993,7.3464319705963135,0.032142662400335566,8192,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,65536,0.375,512.0,512.0,1.0,0.890625,0.0412323087266341,1.08984375,6.998772433185578,0.02334284782409668,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.35280001163482666,0.39692801237106323,0.37662720382213594,0.37196800112724304,0.013401318050665304,1,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.4692479968070984,0.5523840188980103,0.5134752035140991,0.5100640058517456,0.02291433464135784,8,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,64,0.375,0.5,0.5,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.34652799367904663,0.4119040071964264,0.3789471983909607,0.38550400733947754,0.02073945105803335,16,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,128,0.375,1.0,1.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.31462401151657104,0.7456960082054138,0.38617280423641204,0.34545600414276123,0.12230201266253077,32,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,256,0.375,2.0,2.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.32521599531173706,0.419871985912323,0.36325119733810424,0.34968000650405884,0.03161798848223672,64,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,512,0.375,4.0,4.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.289792001247406,0.4663360118865967,0.4091839998960495,0.41655999422073364,0.0446001986506615,128,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,1024,0.375,8.0,8.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.3761279881000519,0.4416320025920868,0.40686399936676027,0.40540799498558044,0.02257778769899645,256,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,2048,0.375,16.0,16.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.7172480225563049,0.8663039803504944,0.7723807990550995,0.7591840028762817,0.04164772379451242,512,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,4096,0.375,32.0,32.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,1.0195519924163818,1.2216639518737793,1.1253888130187988,1.1453600525856018,0.06548005322243594,1024,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8192,0.375,64.0,64.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.7490559816360474,1.9644800424575806,1.8529024004936219,1.814303994178772,0.08042565617327288,2048,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,16384,0.375,128.0,128.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,3.2479360103607178,3.385279893875122,3.296070408821106,3.2800960540771484,0.04525529026442046,4096,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,32768,0.375,256.0,256.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,6.344799995422363,6.517856121063232,6.464438438415527,6.478623867034912,0.05116674443145098,8192,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,65536,0.375,512.0,512.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.2648000121116638,0.325439989566803,0.28852800130844114,0.28390398621559143,0.01933778377635077,1,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.7347840070724487,0.862496018409729,0.7769344031810761,0.769216001033783,0.03290485328796285,8,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,64,0.375,0.5,0.5,0.421875,0.0,1.346291201783626,6.0,5.652114648336087,0.636962890625,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.9198399782180786,0.9646080136299133,0.9412063956260681,0.9411839842796326,0.014939365085478117,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,128,0.375,1.0,1.0,0.5703125,0.0,1.118033988749895,5.0,6.008641773518898,0.580810546875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,1.2796800136566162,1.3484159708023071,1.3006976008415223,1.2929120063781738,0.020807998177176254,32,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,256,0.375,2.0,2.0,0.8828125,0.0,0.6959705453537527,3.0,6.60872850615583,0.38055419921875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,1.3630399703979492,1.4430400133132935,1.3909215927124023,1.3892319798469543,0.022335744492366926,64,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,512,0.375,4.0,4.0,0.984375,0.0,0.5201036555341637,3.0,6.798826509158851,0.28302001953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,1.27948796749115,1.3904000520706177,1.3176063895225525,1.309440016746521,0.038060887827312775,128,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,1024,0.375,8.0,8.0,1.0,0.25,0.3511282039725661,1.875,6.91002266305238,0.1970977783203125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,1.264415979385376,1.3145920038223267,1.2791999936103822,1.2753440141677856,0.014130605249568332,256,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,2048,0.375,16.0,16.0,1.0,0.375,0.24692938483248605,1.6875,6.955481130775285,0.13909912109375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,1.3081920146942139,1.347648024559021,1.3292255997657776,1.329967975616455,0.014558863679016933,512,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,4096,0.375,32.0,32.0,1.0,0.625,0.17143053326165383,1.5625,6.9786675275754035,0.09520339965820312,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,1.242751955986023,1.3112000226974487,1.2747935891151427,1.266207993030548,0.021093073517695057,1024,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8192,0.375,64.0,64.0,1.0,0.78125,0.11000099875256815,1.296875,6.991308871213679,0.062183380126953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.7388160228729248,1.8077759742736816,1.772764801979065,1.772704005241394,0.021056644077284283,2048,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,16384,0.375,128.0,128.0,1.0,0.78125,0.0864630150197678,1.1796875,6.994552526394139,0.048796653747558594,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,2.6563520431518555,2.7063679695129395,2.6785055875778196,2.6791679859161377,0.01639963463052944,4096,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,32768,0.375,256.0,256.0,1.0,0.8671875,0.06127686514721937,1.16015625,6.997291583027146,0.03497934341430664,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,4.386879920959473,4.452256202697754,4.4108480453491214,4.406303882598877,0.019768161791937636,8192,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,65536,0.375,512.0,512.0,1.0,0.884765625,0.041723768525324195,1.1171875,6.998746434318934,0.02298593521118164,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.24208000302314758,0.4028480052947998,0.3041536003351212,0.277103990316391,0.05660721484881584,1,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.2447039932012558,0.30502399802207947,0.26446720361709597,0.26265600323677063,0.016744548364435372,8,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,64,0.375,0.5,0.5,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.2337920069694519,0.2881599962711334,0.26074880361557007,0.264384001493454,0.016469850143940968,16,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,128,0.375,1.0,1.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.23369599878787994,0.28591999411582947,0.25465920120477675,0.25385600328445435,0.01593204652619194,32,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,256,0.375,2.0,2.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.2295999974012375,0.26556798815727234,0.24674240052700042,0.2497600018978119,0.010345732066199003,64,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,512,0.375,4.0,4.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.21721599996089935,0.29020801186561584,0.2394208014011383,0.2346400022506714,0.018747330357768585,128,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,1024,0.375,8.0,8.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.2717759907245636,0.305184006690979,0.28813759982585907,0.28809599578380585,0.01183422600545854,256,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,2048,0.375,16.0,16.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.3917759954929352,0.43772798776626587,0.41130879521369934,0.4131519943475723,0.012992473640805227,512,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,4096,0.375,32.0,32.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,0.6176639795303345,0.7009919881820679,0.642767995595932,0.6330719888210297,0.024074084919938756,1024,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8192,0.375,64.0,64.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.0820800065994263,1.1674879789352417,1.1034304022789,1.0977439880371094,0.0233067292981566,2048,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,16384,0.375,128.0,128.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,1.9809919595718384,2.0415360927581787,2.003715181350708,1.992751955986023,0.022066076434645737,4096,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,32768,0.375,256.0,256.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,3.790112018585205,3.8651199340820312,3.829139161109924,3.8230879306793213,0.025177464160110564,8192,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,65536,0.375,512.0,512.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.212351992726326,0.24383999407291412,0.22760000079870224,0.22723200172185898,0.01050568575837594,1,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.47494399547576904,0.5184000134468079,0.4920704007148743,0.49169600009918213,0.011991064701471855,8,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,64,0.375,0.5,0.5,0.3984375,0.0,1.3919410907075054,6.0,5.570159765557392,0.667236328125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.6360960006713867,0.7004479765892029,0.6608384013175964,0.6572319865226746,0.020416877242438597,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,128,0.375,1.0,1.0,0.625,0.0,1.0307764064044151,4.0,6.138251855282827,0.5382080078125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.780896008014679,0.8301439881324768,0.80346559882164,0.8030399978160858,0.016801230312128875,32,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,256,0.375,2.0,2.0,0.859375,0.0,0.6903350635742038,3.0,6.5943747091218174,0.38067626953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.8607040047645569,0.9195200204849243,0.8783008038997651,0.8751039803028107,0.01719059253115595,64,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,512,0.375,4.0,4.0,0.9765625,0.0,0.49410588440130926,2.75,6.814452474347134,0.271270751953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.833952009677887,0.894752025604248,0.8619967997074127,0.863215982913971,0.018716378851797198,128,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,1024,0.375,8.0,8.0,1.0,0.25,0.33693529145074724,2.125,6.9186075263155535,0.1867218017578125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.834879994392395,0.8871039748191833,0.8651552021503448,0.8638879954814911,0.015262430894400969,256,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,2048,0.375,16.0,16.0,1.0,0.375,0.25567294018677456,1.8125,6.952441049154937,0.14349365234375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.8518080115318298,0.9097599983215332,0.8810272097587586,0.8751040101051331,0.017005819633271906,512,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,4096,0.375,32.0,32.0,1.0,0.625,0.1747801353218523,1.53125,6.978069554482723,0.09820938110351562,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,0.8470079898834229,0.9010239839553833,0.8694015920162201,0.8716959953308105,0.016138881171190216,1024,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8192,0.375,64.0,64.0,1.0,0.65625,0.1158122428154187,1.3125,6.9901908183358845,0.06445503234863281,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.1698240041732788,1.2311359643936157,1.1888479948043824,1.1890720129013062,0.017978797794492758,2048,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,16384,0.375,128.0,128.0,1.0,0.78125,0.08347181893108634,1.1796875,6.994921772573154,0.046871185302734375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,1.7702720165252686,1.8097599744796753,1.7919103980064393,1.7956640124320984,0.012641295676021557,4096,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,32768,0.375,256.0,256.0,1.0,0.78125,0.06866734477822484,1.20703125,6.996602562938728,0.03801727294921875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,2.968672037124634,3.0278079509735107,2.9899007797241213,2.9824799299240112,0.01816414122631667,8192,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,65536,0.375,512.0,512.0,1.0,0.8984375,0.04399546833977376,1.126953125,6.998607314922362,0.024699926376342773,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.19574399292469025,0.2512960135936737,0.21939200013875962,0.2199999988079071,0.017532156418212565,1,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.20483200252056122,0.24006399512290955,0.22215040028095245,0.22433599829673767,0.00969639786132892,8,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,64,0.375,0.5,0.5,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.20559999346733093,0.24726399779319763,0.22126719802618028,0.22207999974489212,0.01328093478485499,16,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,128,0.375,1.0,1.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.20003199577331543,0.2301120012998581,0.21453119963407516,0.21598400175571442,0.010402239855151332,32,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,256,0.375,2.0,2.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.19551999866962433,0.22972799837589264,0.21238719969987868,0.21488000452518463,0.010706095835489097,64,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,512,0.375,4.0,4.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.19420799612998962,0.2903999984264374,0.2211231991648674,0.21476799994707108,0.025955008886196004,128,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,1024,0.375,8.0,8.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.2290560007095337,0.289247989654541,0.2543327987194061,0.24939200282096863,0.01663236753503115,256,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,2048,0.375,16.0,16.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.30831998586654663,0.36953601241111755,0.3324000000953674,0.3288639932870865,0.018617999572156707,512,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,4096,0.375,32.0,32.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,0.462911993265152,0.5497919917106628,0.4893856018781662,0.4816960096359253,0.023348152887178286,1024,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8192,0.375,64.0,64.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,0.7662079930305481,0.8717759847640991,0.788454395532608,0.7744799852371216,0.03174746482604812,2048,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,16384,0.375,128.0,128.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,1.363935947418213,1.4143040180206299,1.3812703967094422,1.3798720240592957,0.014770450075530007,4096,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,32768,0.375,256.0,256.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize +0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,2.5507519245147705,2.680704116821289,2.579859209060669,2.566223978996277,0.03673283558365955,8192,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,65536,0.375,512.0,512.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize diff --git a/runs/frontier-fidelity-envelope-v1/test_fidelity_envelope.py b/runs/frontier-fidelity-envelope-v1/test_fidelity_envelope.py index 3f5a79c..2326466 100644 --- a/runs/frontier-fidelity-envelope-v1/test_fidelity_envelope.py +++ b/runs/frontier-fidelity-envelope-v1/test_fidelity_envelope.py @@ -25,6 +25,27 @@ def load(name: str): class FidelityEnvelopeTest(unittest.TestCase): + def test_block_identities_are_parent_sensitive_and_prefix_stable(self) -> None: + module = load("prepare_exact_trace.py") + prefix = list(range(32)) + left = module.block_identities(prefix + [100, 101], 16) + right = module.block_identities(prefix + [200, 201], 16) + self.assertEqual(left[:2], right[:2]) + self.assertNotEqual(left[2], right[2]) + changed_parent = module.block_identities([999] + prefix[1:] + [100, 101], 16) + self.assertNotEqual(left[0], changed_parent[0]) + self.assertNotEqual(left[1], changed_parent[1]) + + def test_root_sessions_follow_parent_chain(self) -> None: + module = load("prepare_exact_trace.py") + rows = [ + {"chat_id": 10, "parent_chat_id": -1}, + {"chat_id": 11, "parent_chat_id": 10}, + {"chat_id": 12, "parent_chat_id": 11}, + {"chat_id": 20, "parent_chat_id": -1}, + ] + self.assertEqual(module.root_sessions(rows), {10: 10, 11: 10, 12: 10, 20: 20}) + def test_materialize_allreduce(self) -> None: module = load("materialize_frontier_allreduce.py") rows = [] diff --git a/runs/frontier-qwen30-vllm020-profile-v1/freeze_frontier_profiles.py b/runs/frontier-qwen30-vllm020-profile-v1/freeze_frontier_profiles.py index 16f1b68..da2a16d 100644 --- a/runs/frontier-qwen30-vllm020-profile-v1/freeze_frontier_profiles.py +++ b/runs/frontier-qwen30-vllm020-profile-v1/freeze_frontier_profiles.py @@ -638,11 +638,17 @@ def main() -> None: args.output / "moe.csv", args.output / "allreduce.json", ] + batch_composition_augmented = len(args.attention) > 3 manifest = { - "schema_version": "frontier_qwen30_vllm020_frozen_profile.v2", + "schema_version": ( + "frontier_qwen30_vllm020_frozen_profile.v3" + if batch_composition_augmented + else "frontier_qwen30_vllm020_frozen_profile.v2" + ), "profile_id": ( "qwen3-30b-a3b-bf16-vllm020-h20-tp1-2-4-" "fused-mixed-total-conserving" + + ("-pure-prefill-batch-composition" if batch_composition_augmented else "") ), "environment_contract": { "hardware": "NVIDIA H20", @@ -674,6 +680,13 @@ def main() -> None: "ratio, with projected prefill + decode exactly equal to the fused total; " "the split is a schema compatibility attribution, not an observation" ), + "attention_pure_prefill_batch_composition": ( + "Direct FA3 measurements for 2/4 requests at query length 2048 and " + "2/4/8/16 requests at query length 512 for each TP; included only " + "when batch-composition attention inputs are supplied" + if batch_composition_augmented + else "not included" + ), "moe": ( "Replicated gate and fused top-k plus TP-local modular expert kernel; " "expert measurement already includes prepare/finalize so shuffling is zero"