Profile Qwen235 true mixed attention
This commit is contained in:
100
runs/frontier-fidelity-envelope-v1/augment_qwen235_v020_true_mixed_profiles.py
Executable file
100
runs/frontier-fidelity-envelope-v1/augment_qwen235_v020_true_mixed_profiles.py
Executable file
@@ -0,0 +1,100 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Append measured true-mixed attention rows to an immutable Qwen235 profile."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import csv
|
||||
import hashlib
|
||||
import json
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
MODEL = "Qwen3-235B-A22B"
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--base-frozen", type=Path, required=True)
|
||||
parser.add_argument("--cuda-tp4", type=Path, required=True)
|
||||
parser.add_argument("--cuda-tp8", type=Path, required=True)
|
||||
parser.add_argument("--kernel-tp4", type=Path, required=True)
|
||||
parser.add_argument("--kernel-tp8", type=Path, required=True)
|
||||
parser.add_argument("--output-root", type=Path, required=True)
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def digest(path: Path) -> str:
|
||||
value = hashlib.sha256()
|
||||
value.update(path.read_bytes())
|
||||
return value.hexdigest()
|
||||
|
||||
|
||||
def read_rows(path: Path) -> tuple[list[str], list[dict[str, str]]]:
|
||||
with path.open(newline="") as source:
|
||||
reader = csv.DictReader(source)
|
||||
return list(reader.fieldnames or []), list(reader)
|
||||
|
||||
|
||||
def merge_csv(inputs: list[Path], output: Path, measurement_type: str) -> int:
|
||||
fields: list[str] = []
|
||||
rows: list[dict[str, str]] = []
|
||||
true_mixed_count = 0
|
||||
for index, path in enumerate(inputs):
|
||||
input_fields, input_rows = read_rows(path)
|
||||
for field in input_fields:
|
||||
if field not in fields:
|
||||
fields.append(field)
|
||||
if index:
|
||||
for row in input_rows:
|
||||
if row.get("is_true_mixed_batch", "").lower() != "true":
|
||||
raise ValueError(f"non-true-mixed row in {path}")
|
||||
if row.get("measurement_type") != measurement_type:
|
||||
raise ValueError(f"measurement type mismatch in {path}")
|
||||
true_mixed_count += len(input_rows)
|
||||
rows.extend(input_rows)
|
||||
if not fields or not rows or not true_mixed_count:
|
||||
raise ValueError("cannot assemble an empty true-mixed augmentation")
|
||||
with output.open("w", newline="") as target:
|
||||
writer = csv.DictWriter(target, fieldnames=fields, lineterminator="\n")
|
||||
writer.writeheader()
|
||||
writer.writerows(rows)
|
||||
return true_mixed_count
|
||||
|
||||
|
||||
def main() -> None:
|
||||
args = parse_args()
|
||||
output = args.output_root.resolve()
|
||||
if output.exists():
|
||||
raise FileExistsError(output)
|
||||
output.mkdir(parents=True)
|
||||
for name in ("linear_op.csv", "linear_op_kernel_only.csv", "moe.csv", "moe_kernel_only.csv"):
|
||||
shutil.copy2(args.base_frozen / name, output / name)
|
||||
cuda_count = merge_csv(
|
||||
[args.base_frozen / "attention.csv", args.cuda_tp4, args.cuda_tp8],
|
||||
output / "attention.csv",
|
||||
"CUDA_EVENT",
|
||||
)
|
||||
kernel_count = merge_csv(
|
||||
[args.base_frozen / "attention_kernel_only.csv", args.kernel_tp4, args.kernel_tp8],
|
||||
output / "attention_kernel_only.csv",
|
||||
"KERNEL_ONLY",
|
||||
)
|
||||
base_manifest = json.loads((args.base_frozen / "manifest.json").read_text())
|
||||
manifest = {
|
||||
**base_manifest,
|
||||
"schema": "qwen235-v020-frontier-profile-v2-true-mixed",
|
||||
"true_mixed_inputs": {
|
||||
name: str(getattr(args, name).resolve())
|
||||
for name in ("cuda_tp4", "cuda_tp8", "kernel_tp4", "kernel_tp8")
|
||||
},
|
||||
"true_mixed_rows": {"CUDA_EVENT": cuda_count, "KERNEL_ONLY": kernel_count},
|
||||
"outputs": {path.name: digest(path) for path in sorted(output.glob("*.csv"))},
|
||||
}
|
||||
(output / "manifest.json").write_text(json.dumps(manifest, indent=2, sort_keys=True) + "\n")
|
||||
print(json.dumps(manifest, sort_keys=True))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -181,8 +181,10 @@ def main() -> None:
|
||||
run_dir = args.output_root / "runs" / config.name / trace["label"]
|
||||
result_path = run_dir / "result.json"
|
||||
if args.resume and result_path.is_file():
|
||||
results.append(json.loads(result_path.read_text()))
|
||||
continue
|
||||
previous = json.loads(result_path.read_text())
|
||||
if previous.get("status") == "completed":
|
||||
results.append(previous)
|
||||
continue
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
command = builder.build_frontier_command(
|
||||
python_bin="/usr/bin/python3",
|
||||
|
||||
51
runs/frontier-fidelity-envelope-v1/run_qwen235_v020_true_mixed_profiles.sh
Executable file
51
runs/frontier-fidelity-envelope-v1/run_qwen235_v020_true_mixed_profiles.sh
Executable file
@@ -0,0 +1,51 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
OUTPUT_ROOT="${OUTPUT_ROOT:?OUTPUT_ROOT is required}"
|
||||
FRONTIER_SOURCE="${FRONTIER_SOURCE:-/home/admin/cpfs/wjh/aituner/frontier-q235-v020-5b953f5}"
|
||||
VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
|
||||
MODEL=Qwen3-235B-A22B
|
||||
PREFILL_BATCHES=(1 2 4 8)
|
||||
PREFILL_CHUNKS=(128 512 2048 8192)
|
||||
DECODE_BATCHES=(1 8 32 64 120)
|
||||
DECODE_KV=(128 1024 4096 16384 32768)
|
||||
|
||||
mkdir -p "${OUTPUT_ROOT}/logs" "${OUTPUT_ROOT}/provenance"
|
||||
exec > >(tee -a "${OUTPUT_ROOT}/controller.log") 2>&1
|
||||
|
||||
echo "Q235_TRUE_MIXED_PROFILE_LAUNCH_ECHO host=dash0 model=${MODEL} vllm=0.20.0 frontier=$(git -C "${FRONTIER_SOURCE}" rev-parse HEAD) device=H20 methods={CUDA_EVENT,KERNEL_ONLY} tp={4,8} grid=4x4x5x5 parallel_gpus=4 expected_wall=10-30m expected_cost=0.7-2_H20-GPUh output=${OUTPUT_ROOT}"
|
||||
date -u +START_UTC=%Y-%m-%dT%H:%M:%SZ
|
||||
nvidia-smi --query-gpu=index,memory.used --format=csv,noheader,nounits \
|
||||
| awk '$2 > 16 {exit 1}'
|
||||
git -C "${FRONTIER_SOURCE}" rev-parse HEAD > "${OUTPUT_ROOT}/provenance/frontier.commit"
|
||||
"${VENV_ROOT}/bin/vllm" --version > "${OUTPUT_ROOT}/provenance/vllm.version"
|
||||
cd "${FRONTIER_SOURCE}"
|
||||
|
||||
profile() {
|
||||
local gpu="$1" method="$2" tp="$3" root="$4"
|
||||
env CUDA_VISIBLE_DEVICES="${gpu}" PYTHONPATH="${FRONTIER_SOURCE}" \
|
||||
"${VENV_ROOT}/bin/python" -m frontier.profiling.attention.main \
|
||||
--disable_ray --num_gpus 1 --device h20 --output_dir "${root}" --models "${MODEL}" \
|
||||
--num_tensor_parallel_workers "${tp}" --max_model_len 40960 --max_seq_len 40960 \
|
||||
--max_batch_size 128 --batch_size_list 1 --decode_kv_cache_size_list 128 \
|
||||
--fixed_chunked_prefill_size 8192 --attention_backend FLASHINFER \
|
||||
--enable_true_mixed \
|
||||
--true_mixed_prefill_batch_sizes "${PREFILL_BATCHES[@]}" \
|
||||
--true_mixed_prefill_chunk_sizes "${PREFILL_CHUNKS[@]}" \
|
||||
--true_mixed_decode_batch_sizes "${DECODE_BATCHES[@]}" \
|
||||
--true_mixed_decode_kv_cache_sizes "${DECODE_KV[@]}" \
|
||||
--true_mixed_prefill_kv_cache_size 0 \
|
||||
--profile_method "${method}" --yes
|
||||
}
|
||||
|
||||
declare -a pids=()
|
||||
profile 0 cuda_event 4 "${OUTPUT_ROOT}/cuda-tp4" > "${OUTPUT_ROOT}/logs/cuda-tp4.log" 2>&1 & pids+=("$!")
|
||||
profile 1 record_function 4 "${OUTPUT_ROOT}/kernel-tp4" > "${OUTPUT_ROOT}/logs/kernel-tp4.log" 2>&1 & pids+=("$!")
|
||||
profile 2 cuda_event 8 "${OUTPUT_ROOT}/cuda-tp8" > "${OUTPUT_ROOT}/logs/cuda-tp8.log" 2>&1 & pids+=("$!")
|
||||
profile 3 record_function 8 "${OUTPUT_ROOT}/kernel-tp8" > "${OUTPUT_ROOT}/logs/kernel-tp8.log" 2>&1 & pids+=("$!")
|
||||
failed=0
|
||||
for pid in "${pids[@]}"; do wait "${pid}" || failed=1; done
|
||||
[[ "${failed}" -eq 0 ]] || { tail -n 80 "${OUTPUT_ROOT}"/logs/*.log; exit 1; }
|
||||
date -u +END_UTC=%Y-%m-%dT%H:%M:%SZ
|
||||
echo Q235_V020_TRUE_MIXED_PROFILES_COMPLETE
|
||||
Reference in New Issue
Block a user