Record structured attention experiment verdict
This commit is contained in:
3
runs/frontier-attn-structured-v0/.gitignore
vendored
Normal file
3
runs/frontier-attn-structured-v0/.gitignore
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
__pycache__/
|
||||
cache/
|
||||
replay/
|
||||
@@ -0,0 +1,249 @@
|
||||
From 1f8900a4ac64e45754b03d0aa7c1dddab65785cf Mon Sep 17 00:00:00 2001
|
||||
From: Gahow Wang <gahow.wang@gmail.com>
|
||||
Date: Thu, 23 Jul 2026 15:27:40 +0800
|
||||
Subject: [PATCH] Experiment with structured attention prefill predictor
|
||||
|
||||
---
|
||||
.../shared_prediction_model_manager.py | 16 +++-
|
||||
.../sklearn_execution_time_predictor.py | 16 +++-
|
||||
.../structured_attention_prefill.py | 79 +++++++++++++++++++
|
||||
.../unit/test_structured_attention_prefill.py | 59 ++++++++++++++
|
||||
4 files changed, 165 insertions(+), 5 deletions(-)
|
||||
create mode 100644 frontier/execution_time_predictor/structured_attention_prefill.py
|
||||
create mode 100644 tests/unit/test_structured_attention_prefill.py
|
||||
|
||||
diff --git a/frontier/execution_time_predictor/shared_prediction_model_manager.py b/frontier/execution_time_predictor/shared_prediction_model_manager.py
|
||||
index 8a65a49..4a21165 100644
|
||||
--- a/frontier/execution_time_predictor/shared_prediction_model_manager.py
|
||||
+++ b/frontier/execution_time_predictor/shared_prediction_model_manager.py
|
||||
@@ -19,6 +19,9 @@ from frontier.execution_time_predictor.attention_tp_policy import (
|
||||
from frontier.execution_time_predictor.attention_dataset_contract import (
|
||||
enforce_mixed_attention_input_contract,
|
||||
)
|
||||
+from frontier.execution_time_predictor.structured_attention_prefill import (
|
||||
+ StructuredAttentionPrefillRegressor,
|
||||
+)
|
||||
from frontier.logger import init_logger
|
||||
from frontier.moe_gating_runtime import (
|
||||
DEFAULT_MOE_GATING_RUNTIME_CONTEXT,
|
||||
@@ -1254,7 +1257,10 @@ class ExecutionTimePredictionModelManager:
|
||||
raise ValueError(
|
||||
"Missing required column 'prefill_chunk_size' in attention profiling data."
|
||||
)
|
||||
- standard_prefill_df = prefill_df[prefill_df["prefill_chunk_size"] > 0].copy()
|
||||
+ standard_prefill_df = prefill_df[
|
||||
+ (prefill_df["prefill_chunk_size"] > 0)
|
||||
+ & (prefill_df["batch_size"] == 1)
|
||||
+ ].copy()
|
||||
|
||||
prefill_model_signature = f"attn_prefill_{attention_signature}"
|
||||
if prefill_model_signature not in trained_model_signatures:
|
||||
@@ -1742,7 +1748,13 @@ class ExecutionTimePredictionModelManager:
|
||||
# initialization to generate missing cache files.
|
||||
# ============================================================
|
||||
|
||||
- estimator, grid_search_params = self._create_estimator_and_params(execution_time_predictor_config)
|
||||
+ if model_name == "attn_prefill":
|
||||
+ estimator = StructuredAttentionPrefillRegressor()
|
||||
+ grid_search_params = {}
|
||||
+ else:
|
||||
+ estimator, grid_search_params = self._create_estimator_and_params(
|
||||
+ execution_time_predictor_config
|
||||
+ )
|
||||
|
||||
cv = min(execution_time_predictor_config.k_fold_cv_splits, len(df)) if len(df) >= 2 else 2
|
||||
|
||||
diff --git a/frontier/execution_time_predictor/sklearn_execution_time_predictor.py b/frontier/execution_time_predictor/sklearn_execution_time_predictor.py
|
||||
index 27b62bf..b7f5350 100644
|
||||
--- a/frontier/execution_time_predictor/sklearn_execution_time_predictor.py
|
||||
+++ b/frontier/execution_time_predictor/sklearn_execution_time_predictor.py
|
||||
@@ -45,6 +45,9 @@ from frontier.execution_time_predictor.attention_tp_policy import (
|
||||
from frontier.execution_time_predictor.attention_dataset_contract import (
|
||||
enforce_mixed_attention_input_contract,
|
||||
)
|
||||
+from frontier.execution_time_predictor.structured_attention_prefill import (
|
||||
+ StructuredAttentionPrefillRegressor,
|
||||
+)
|
||||
from frontier.logger import init_logger
|
||||
from frontier.moe_gating_runtime import get_moe_gating_base_model_name
|
||||
from frontier.profiling.cpu_overhead.schema import (
|
||||
@@ -2573,8 +2576,12 @@ class SklearnExecutionTimePredictor(BaseExecutionTimePredictor):
|
||||
if cached_model:
|
||||
return cached_model
|
||||
|
||||
- model = self._get_estimator()
|
||||
- grid_search_params = self._get_grid_search_params()
|
||||
+ if model_name == "attn_prefill":
|
||||
+ model = StructuredAttentionPrefillRegressor()
|
||||
+ grid_search_params = {}
|
||||
+ else:
|
||||
+ model = self._get_estimator()
|
||||
+ grid_search_params = self._get_grid_search_params()
|
||||
|
||||
if len(df) < self._config.k_fold_cv_splits:
|
||||
cv = 2
|
||||
@@ -2869,7 +2876,10 @@ class SklearnExecutionTimePredictor(BaseExecutionTimePredictor):
|
||||
raise ValueError(
|
||||
"Missing required column 'prefill_chunk_size' in attention profiling data."
|
||||
)
|
||||
- standard_prefill_df = prefill_df[prefill_df["prefill_chunk_size"] > 0].copy()
|
||||
+ standard_prefill_df = prefill_df[
|
||||
+ (prefill_df["prefill_chunk_size"] > 0)
|
||||
+ & (prefill_df["batch_size"] == 1)
|
||||
+ ].copy()
|
||||
if len(standard_prefill_df) == 0:
|
||||
raise ValueError(
|
||||
"No standard prefill rows (prefill_chunk_size > 0) found in eager attention profiling data."
|
||||
diff --git a/frontier/execution_time_predictor/structured_attention_prefill.py b/frontier/execution_time_predictor/structured_attention_prefill.py
|
||||
new file mode 100644
|
||||
index 0000000..1829047
|
||||
--- /dev/null
|
||||
+++ b/frontier/execution_time_predictor/structured_attention_prefill.py
|
||||
@@ -0,0 +1,79 @@
|
||||
+"""Structured latency model for single-request chunked prefill attention."""
|
||||
+
|
||||
+from typing import Any
|
||||
+
|
||||
+import numpy as np
|
||||
+from sklearn.base import BaseEstimator, RegressorMixin
|
||||
+from sklearn.isotonic import IsotonicRegression
|
||||
+from sklearn.linear_model import LinearRegression
|
||||
+
|
||||
+
|
||||
+class StructuredAttentionPrefillRegressor(RegressorMixin, BaseEstimator):
|
||||
+ """Model attention as a monotone base curve plus continuous KV growth.
|
||||
+
|
||||
+ Input columns retain the existing Frontier contract:
|
||||
+ ``[kv_cache_size, prefill_chunk_size_squared]``.
|
||||
+ """
|
||||
+
|
||||
+ def fit(self, X: Any, y: Any) -> "StructuredAttentionPrefillRegressor":
|
||||
+ values = self._as_feature_array(X)
|
||||
+ target = np.asarray(y, dtype=float)
|
||||
+ kv_cache_size = values[:, 0]
|
||||
+ prefill_chunk_size = np.sqrt(np.maximum(values[:, 1], 0.0))
|
||||
+
|
||||
+ base_mask = np.isclose(kv_cache_size, 0.0)
|
||||
+ growth_mask = kv_cache_size > 0.0
|
||||
+ if not np.any(base_mask) or not np.any(growth_mask):
|
||||
+ raise ValueError(
|
||||
+ "structured attn_prefill training requires both KV=0 base rows "
|
||||
+ "and KV>0 growth rows"
|
||||
+ )
|
||||
+
|
||||
+ base_q = prefill_chunk_size[base_mask]
|
||||
+ base_y = target[base_mask]
|
||||
+ unique_q = np.unique(base_q)
|
||||
+ grouped_y = np.asarray(
|
||||
+ [np.mean(base_y[np.isclose(base_q, q)]) for q in unique_q],
|
||||
+ dtype=float,
|
||||
+ )
|
||||
+ self._base_model = IsotonicRegression(
|
||||
+ increasing=True,
|
||||
+ out_of_bounds="clip",
|
||||
+ ).fit(unique_q, grouped_y)
|
||||
+
|
||||
+ growth_q = prefill_chunk_size[growth_mask]
|
||||
+ growth_kv = kv_cache_size[growth_mask]
|
||||
+ growth_base = self._base_model.predict(growth_q)
|
||||
+ growth_features = np.column_stack(
|
||||
+ (growth_kv, growth_q * growth_kv)
|
||||
+ )
|
||||
+ self._growth_model = LinearRegression(
|
||||
+ fit_intercept=False,
|
||||
+ positive=True,
|
||||
+ ).fit(growth_features, target[growth_mask] - growth_base)
|
||||
+
|
||||
+ self.n_features_in_ = 2
|
||||
+ self._frontier_base_q_min = float(unique_q.min())
|
||||
+ self._frontier_base_q_max = float(unique_q.max())
|
||||
+ self._frontier_growth_kv_max = float(growth_kv.max())
|
||||
+ return self
|
||||
+
|
||||
+ def predict(self, X: Any) -> np.ndarray:
|
||||
+ values = self._as_feature_array(X)
|
||||
+ kv_cache_size = values[:, 0]
|
||||
+ prefill_chunk_size = np.sqrt(np.maximum(values[:, 1], 0.0))
|
||||
+ base = self._base_model.predict(prefill_chunk_size)
|
||||
+ growth_features = np.column_stack(
|
||||
+ (kv_cache_size, prefill_chunk_size * kv_cache_size)
|
||||
+ )
|
||||
+ return np.maximum(base + self._growth_model.predict(growth_features), 0.0)
|
||||
+
|
||||
+ @staticmethod
|
||||
+ def _as_feature_array(X: Any) -> np.ndarray:
|
||||
+ values = np.asarray(X, dtype=float)
|
||||
+ if values.ndim != 2 or values.shape[1] != 2:
|
||||
+ raise ValueError(
|
||||
+ "structured attn_prefill expects exactly two features: "
|
||||
+ "kv_cache_size and prefill_chunk_size_squared"
|
||||
+ )
|
||||
+ return values
|
||||
diff --git a/tests/unit/test_structured_attention_prefill.py b/tests/unit/test_structured_attention_prefill.py
|
||||
new file mode 100644
|
||||
index 0000000..12c4247
|
||||
--- /dev/null
|
||||
+++ b/tests/unit/test_structured_attention_prefill.py
|
||||
@@ -0,0 +1,59 @@
|
||||
+import pickle
|
||||
+import unittest
|
||||
+
|
||||
+import numpy as np
|
||||
+
|
||||
+from frontier.execution_time_predictor.structured_attention_prefill import (
|
||||
+ StructuredAttentionPrefillRegressor,
|
||||
+)
|
||||
+
|
||||
+
|
||||
+class StructuredAttentionPrefillRegressorTest(unittest.TestCase):
|
||||
+ def setUp(self) -> None:
|
||||
+ q = np.asarray([64, 128, 256, 512, 1024, 2048, 4096, 8192], dtype=float)
|
||||
+ base = 0.05 + 1e-4 * q + 4e-8 * q**2
|
||||
+ context_q = np.asarray([2048, 4096, 8192] * 3, dtype=float)
|
||||
+ context_kv = np.repeat([8192, 16384, 24576], 3).astype(float)
|
||||
+ context_y = (
|
||||
+ np.interp(context_q, q, base)
|
||||
+ + 1.5e-5 * context_kv
|
||||
+ + 3e-8 * context_q * context_kv
|
||||
+ )
|
||||
+ self.X = np.column_stack(
|
||||
+ (
|
||||
+ np.concatenate((np.zeros_like(q), context_kv)),
|
||||
+ np.concatenate((q**2, context_q**2)),
|
||||
+ )
|
||||
+ )
|
||||
+ self.y = np.concatenate((base, context_y))
|
||||
+
|
||||
+ def test_recovers_structured_curve(self) -> None:
|
||||
+ model = StructuredAttentionPrefillRegressor().fit(self.X, self.y)
|
||||
+ np.testing.assert_allclose(model.predict(self.X), self.y, rtol=1e-6)
|
||||
+
|
||||
+ def test_prediction_is_nonnegative_and_monotone(self) -> None:
|
||||
+ model = StructuredAttentionPrefillRegressor().fit(self.X, self.y)
|
||||
+ q = np.arange(1, 8193, dtype=float)
|
||||
+ for kv in (0, 8192, 32768, 40912):
|
||||
+ X = np.column_stack((np.full_like(q, kv), q**2))
|
||||
+ prediction = model.predict(X)
|
||||
+ self.assertTrue(np.all(prediction >= 0))
|
||||
+ self.assertTrue(np.all(np.diff(prediction) >= -1e-12))
|
||||
+
|
||||
+ kv = np.arange(0, 40913, 64, dtype=float)
|
||||
+ for q_value in (64, 2048, 8192):
|
||||
+ X = np.column_stack((kv, np.full_like(kv, q_value**2)))
|
||||
+ self.assertTrue(np.all(np.diff(model.predict(X)) >= -1e-12))
|
||||
+
|
||||
+ def test_pickle_round_trip(self) -> None:
|
||||
+ model = StructuredAttentionPrefillRegressor().fit(self.X, self.y)
|
||||
+ restored = pickle.loads(pickle.dumps(model))
|
||||
+ np.testing.assert_allclose(restored.predict(self.X), self.y, rtol=1e-6)
|
||||
+
|
||||
+ def test_requires_base_and_growth_rows(self) -> None:
|
||||
+ with self.assertRaisesRegex(ValueError, "KV=0 base rows"):
|
||||
+ StructuredAttentionPrefillRegressor().fit(self.X[:8], self.y[:8])
|
||||
+
|
||||
+
|
||||
+if __name__ == "__main__":
|
||||
+ unittest.main()
|
||||
--
|
||||
2.43.0
|
||||
|
||||
256
runs/frontier-attn-structured-v0/analyze_predictor_ablation.py
Normal file
256
runs/frontier-attn-structured-v0/analyze_predictor_ablation.py
Normal file
@@ -0,0 +1,256 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Offline predictor ablation for EXP-ATTN-STRUCTURED.
|
||||
|
||||
This is deliberately profile-only: it decides whether the structured model is
|
||||
good enough to justify the expensive 7-cell trace replay.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import csv
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
|
||||
ROOT = Path(__file__).resolve().parent
|
||||
REPO = ROOT.parents[1]
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"--profile",
|
||||
type=Path,
|
||||
default=REPO
|
||||
/ "runs/frontier-prefill-kvgrowth-fix-v0/profiles/"
|
||||
"profile-v5-kvgrowth/attention.csv",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--frontier-checkout",
|
||||
type=Path,
|
||||
default=Path("/tmp/frontier-attn-structured-v0"),
|
||||
)
|
||||
parser.add_argument("--output-root", type=Path, default=ROOT / "results")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def normalize_bool(series: pd.Series) -> pd.Series:
|
||||
return series.astype(str).str.strip().str.lower().isin(
|
||||
{"1", "true", "t", "yes", "y"}
|
||||
)
|
||||
|
||||
|
||||
def load_profile(path: Path) -> pd.DataFrame:
|
||||
df = pd.read_csv(path).drop_duplicates()
|
||||
for column in ("is_prefill", "is_true_mixed_batch"):
|
||||
df[column] = normalize_bool(df[column])
|
||||
df = df[
|
||||
(df["n_embd"] == 2048)
|
||||
& (df["n_q_head"] == 32)
|
||||
& (df["n_kv_head"] == 4)
|
||||
& (df["block_size"] == 16)
|
||||
& df["is_prefill"]
|
||||
& ~df["is_true_mixed_batch"]
|
||||
& (df["prefill_chunk_size"] > 0)
|
||||
].copy()
|
||||
df["prefill_chunk_size_squared"] = df["prefill_chunk_size"] ** 2
|
||||
return df
|
||||
|
||||
|
||||
def mape(actual: np.ndarray, predicted: np.ndarray) -> float:
|
||||
return float(np.mean(np.abs((predicted - actual) / actual)) * 100)
|
||||
|
||||
|
||||
def make_rf() -> RandomForestRegressor:
|
||||
# Exact best parameters selected by the current profile-v5 GridSearchCV.
|
||||
return RandomForestRegressor(
|
||||
random_state=0,
|
||||
n_estimators=250,
|
||||
max_depth=8,
|
||||
min_samples_split=2,
|
||||
)
|
||||
|
||||
|
||||
def features(df: pd.DataFrame) -> pd.DataFrame:
|
||||
return df[["kv_cache_size", "prefill_chunk_size_squared"]]
|
||||
|
||||
|
||||
def score_model(
|
||||
name: str,
|
||||
estimator: Any,
|
||||
train: pd.DataFrame,
|
||||
single: pd.DataFrame,
|
||||
grid: pd.DataFrame,
|
||||
) -> dict[str, Any]:
|
||||
target = "time_stats.attn_prefill.median"
|
||||
estimator.fit(features(train), train[target])
|
||||
grid_prediction = estimator.predict(features(grid))
|
||||
single_prediction = estimator.predict(features(single))
|
||||
|
||||
heldout_actual: list[float] = []
|
||||
heldout_prediction: list[float] = []
|
||||
for context in sorted(grid["kv_cache_size"].unique()):
|
||||
test = grid[grid["kv_cache_size"] == context]
|
||||
fold_train = train.drop(index=test.index, errors="ignore")
|
||||
fold_model = (
|
||||
make_rf()
|
||||
if name.startswith("rf")
|
||||
else estimator.__class__()
|
||||
)
|
||||
fold_model.fit(features(fold_train), fold_train[target])
|
||||
heldout_actual.extend(test[target].astype(float))
|
||||
heldout_prediction.extend(fold_model.predict(features(test)))
|
||||
|
||||
q = np.arange(1, 8193, dtype=float)
|
||||
q_deltas: list[float] = []
|
||||
prediction_min: list[float] = []
|
||||
for context in (0, 8192, 16384, 24576, 32768, 40912):
|
||||
X = pd.DataFrame(
|
||||
{
|
||||
"kv_cache_size": np.full_like(q, context),
|
||||
"prefill_chunk_size_squared": q**2,
|
||||
}
|
||||
)
|
||||
prediction = estimator.predict(X)
|
||||
prediction_min.append(float(prediction.min()))
|
||||
q_deltas.append(float(np.diff(prediction).min()))
|
||||
|
||||
kv = np.arange(0, 40913, 64, dtype=float)
|
||||
kv_deltas: list[float] = []
|
||||
for query in (64, 512, 2048, 4096, 8192):
|
||||
X = pd.DataFrame(
|
||||
{
|
||||
"kv_cache_size": kv,
|
||||
"prefill_chunk_size_squared": np.full_like(kv, query**2),
|
||||
}
|
||||
)
|
||||
kv_deltas.append(float(np.diff(estimator.predict(X)).min()))
|
||||
|
||||
heldout_actual_array = np.asarray(heldout_actual)
|
||||
heldout_prediction_array = np.asarray(heldout_prediction)
|
||||
return {
|
||||
"candidate": name,
|
||||
"training_rows": len(train),
|
||||
"grid_fit_mape_pct": mape(
|
||||
grid[target].to_numpy(), np.asarray(grid_prediction)
|
||||
),
|
||||
"single_fit_mape_pct": mape(
|
||||
single[target].to_numpy(), np.asarray(single_prediction)
|
||||
),
|
||||
"heldout_context_mape_pct": mape(
|
||||
heldout_actual_array, heldout_prediction_array
|
||||
),
|
||||
"heldout_context_max_abs_error_pct": float(
|
||||
np.max(
|
||||
np.abs(
|
||||
(heldout_prediction_array - heldout_actual_array)
|
||||
/ heldout_actual_array
|
||||
)
|
||||
)
|
||||
* 100
|
||||
),
|
||||
"prediction_min_ms": min(prediction_min),
|
||||
"q_min_delta_ms": min(q_deltas),
|
||||
"kv_min_delta_ms": min(kv_deltas),
|
||||
"monotone_and_nonnegative": (
|
||||
min(prediction_min) >= 0
|
||||
and min(q_deltas) >= -1e-12
|
||||
and min(kv_deltas) >= -1e-12
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def main() -> None:
|
||||
args = parse_args()
|
||||
sys.path.insert(0, str(args.frontier_checkout))
|
||||
from frontier.execution_time_predictor.structured_attention_prefill import (
|
||||
StructuredAttentionPrefillRegressor,
|
||||
)
|
||||
|
||||
df = load_profile(args.profile)
|
||||
records: list[dict[str, Any]] = []
|
||||
data_audit: dict[str, Any] = {}
|
||||
for tp in (1, 2, 4):
|
||||
tp_df = df[df["num_tensor_parallel_workers"] == tp].copy()
|
||||
single = tp_df[tp_df["batch_size"] == 1].copy()
|
||||
grid = single[
|
||||
single["prefill_chunk_size"].isin((2048, 4096, 8192))
|
||||
& (single["kv_cache_size"] > 0)
|
||||
].copy()
|
||||
duplicate_groups = (
|
||||
tp_df.groupby(
|
||||
["kv_cache_size", "prefill_chunk_size_squared"]
|
||||
)
|
||||
.size()
|
||||
.gt(1)
|
||||
.sum()
|
||||
)
|
||||
data_audit[f"tp{tp}"] = {
|
||||
"standard_rows": len(tp_df),
|
||||
"single_request_rows": len(single),
|
||||
"target_grid_rows": len(grid),
|
||||
"duplicate_feature_groups": int(duplicate_groups),
|
||||
}
|
||||
|
||||
candidates = (
|
||||
("rf_all", make_rf(), tp_df),
|
||||
("rf_single", make_rf(), single),
|
||||
(
|
||||
"structured_single",
|
||||
StructuredAttentionPrefillRegressor(),
|
||||
single,
|
||||
),
|
||||
)
|
||||
for name, model, train in candidates:
|
||||
result = score_model(name, model, train, single, grid)
|
||||
result["tp"] = tp
|
||||
records.append(result)
|
||||
|
||||
structured = [r for r in records if r["candidate"] == "structured_single"]
|
||||
checks = {
|
||||
"heldout_context_mape_le_5pct": all(
|
||||
r["heldout_context_mape_pct"] <= 5 for r in structured
|
||||
),
|
||||
"monotone_and_nonnegative": all(
|
||||
r["monotone_and_nonnegative"] for r in structured
|
||||
),
|
||||
}
|
||||
checks["profile_gate"] = all(checks.values())
|
||||
payload = {
|
||||
"schema": "frontier-attn-structured-ablation-v1",
|
||||
"profile": str(args.profile.resolve()),
|
||||
"frontier_checkout": str(args.frontier_checkout.resolve()),
|
||||
"data_audit": data_audit,
|
||||
"results": records,
|
||||
"checks": checks,
|
||||
}
|
||||
|
||||
args.output_root.mkdir(parents=True, exist_ok=True)
|
||||
(args.output_root / "predictor-ablation.json").write_text(
|
||||
json.dumps(payload, indent=2)
|
||||
)
|
||||
with (args.output_root / "predictor-ablation.csv").open(
|
||||
"w", newline=""
|
||||
) as stream:
|
||||
writer = csv.DictWriter(stream, fieldnames=list(records[0]))
|
||||
writer.writeheader()
|
||||
writer.writerows(records)
|
||||
print(json.dumps(checks, indent=2))
|
||||
for row in records:
|
||||
print(
|
||||
f"TP{row['tp']} {row['candidate']:18s} "
|
||||
f"grid={row['grid_fit_mape_pct']:.2f}% "
|
||||
f"heldout={row['heldout_context_mape_pct']:.2f}% "
|
||||
f"max={row['heldout_context_max_abs_error_pct']:.2f}% "
|
||||
f"monotone={row['monotone_and_nonnegative']}"
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
304
runs/frontier-attn-structured-v0/analyze_trace_verdict.py
Normal file
304
runs/frontier-attn-structured-v0/analyze_trace_verdict.py
Normal file
@@ -0,0 +1,304 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Trial-aware verdict for the seven structured-attention trace replays."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import csv
|
||||
import json
|
||||
import math
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
ROOT = Path(__file__).resolve().parent
|
||||
REPO = ROOT.parents[1]
|
||||
S3_REAL = REPO / "runs/frontier-s3-real-v0"
|
||||
V5 = REPO / "runs/frontier-prefill-kvgrowth-fix-v0"
|
||||
|
||||
CELLS = {
|
||||
"tp1_rho0p00125": {
|
||||
"real": "frontier-tp1-real-r0p00125-t*",
|
||||
"old": V5 / "sim-replay-tp1/v5/tp1_rho0p00125",
|
||||
},
|
||||
"tp1_rho0p0025": {
|
||||
"real": "frontier-tp1-real-r0p0025-t*",
|
||||
"old": V5 / "sim-replay-tp1/v5/tp1_rho0p0025",
|
||||
},
|
||||
"tp2_rho0p0025": {
|
||||
"real": "frontier-s3-real-full-r0p0025-tp2-t*",
|
||||
"old": V5 / "sim-replay/tp2_rho0p0025",
|
||||
},
|
||||
"tp2_rho0p005": {
|
||||
"real": "frontier-s3-real-full-r0p005-tp2-t*",
|
||||
"old": V5 / "sim-replay/tp2_rho0p005",
|
||||
},
|
||||
"tp4_rho0p0025": {
|
||||
"real": "frontier-s3-real-full-r0p0025-tp4-t*",
|
||||
"old": V5 / "sim-replay/tp4_rho0p0025",
|
||||
},
|
||||
"tp4_rho0p005": {
|
||||
"real": "frontier-s3-real-full-r0p005-tp4-t*",
|
||||
"old": V5 / "sim-replay/tp4_rho0p005",
|
||||
},
|
||||
"tp4_rho0p01": {
|
||||
"real": "frontier-s3-real-full-r0p01-tp4-t*",
|
||||
"old": V5 / "sim-replay/tp4_rho0p01",
|
||||
},
|
||||
}
|
||||
METRICS = {
|
||||
"ttft": ("ttft_ms", "ttft"),
|
||||
"tpot": ("tpot_ms", "tpot"),
|
||||
"e2e": ("e2e_ms", "request_e2e_time"),
|
||||
}
|
||||
QUANTILES = {"mean": None, "p50": 0.5, "p90": 0.9, "p99": 0.99}
|
||||
|
||||
|
||||
def percentile(values: list[float], quantile: float) -> float:
|
||||
ordered = sorted(values)
|
||||
position = (len(ordered) - 1) * quantile
|
||||
lower, upper = math.floor(position), math.ceil(position)
|
||||
if lower == upper:
|
||||
return ordered[lower]
|
||||
return (
|
||||
ordered[lower] * (upper - position)
|
||||
+ ordered[upper] * (position - lower)
|
||||
)
|
||||
|
||||
|
||||
def summarize(values: list[float]) -> dict[str, float]:
|
||||
return {
|
||||
name: (
|
||||
sum(values) / len(values)
|
||||
if quantile is None
|
||||
else percentile(values, quantile)
|
||||
)
|
||||
for name, quantile in QUANTILES.items()
|
||||
}
|
||||
|
||||
|
||||
def load_real_trials(pattern: str) -> list[list[dict[str, Any]]]:
|
||||
trials = []
|
||||
for run_root in sorted((S3_REAL / "fleet-artifacts").glob(pattern)):
|
||||
results = list(
|
||||
run_root.glob(
|
||||
"artifacts/outputs/full-real/*/*/trial-*/results/result.json"
|
||||
)
|
||||
)
|
||||
if len(results) != 1:
|
||||
raise ValueError(f"expected one result in {run_root}, got {results}")
|
||||
trials.append(json.loads(results[0].read_text())["requests"])
|
||||
if len(trials) != 2:
|
||||
raise ValueError(f"expected two real trials for {pattern}, got {len(trials)}")
|
||||
return trials
|
||||
|
||||
|
||||
def load_sim(root: Path) -> list[dict[str, str]]:
|
||||
matches = list((root / "metrics").rglob("request_metrics.csv"))
|
||||
if len(matches) != 1:
|
||||
raise ValueError(f"expected one request_metrics.csv below {root}: {matches}")
|
||||
rows = list(csv.DictReader(matches[0].open()))
|
||||
rows.sort(key=lambda row: int(float(row["Request Id"])))
|
||||
return rows
|
||||
|
||||
|
||||
def distribution_bias(
|
||||
real_rows: list[dict[str, Any]],
|
||||
sim_rows: list[dict[str, str]],
|
||||
) -> dict[str, dict[str, float]]:
|
||||
output: dict[str, dict[str, float]] = {}
|
||||
for metric, (real_key, sim_key) in METRICS.items():
|
||||
pairs = [
|
||||
(float(real[real_key]), float(sim[sim_key]))
|
||||
for real, sim in zip(real_rows, sim_rows)
|
||||
if real.get("success")
|
||||
]
|
||||
real_summary = summarize([pair[0] for pair in pairs])
|
||||
sim_summary = summarize([pair[1] for pair in pairs])
|
||||
output[metric] = {
|
||||
name: (sim_summary[name] - real_summary[name]) / real_summary[name]
|
||||
for name in QUANTILES
|
||||
}
|
||||
return output
|
||||
|
||||
|
||||
def paired_relative_error(
|
||||
real_rows: list[dict[str, Any]],
|
||||
sim_rows: list[dict[str, str]],
|
||||
) -> dict[str, dict[str, float]]:
|
||||
output: dict[str, dict[str, float]] = {}
|
||||
for metric, (real_key, sim_key) in METRICS.items():
|
||||
errors = [
|
||||
(float(sim[sim_key]) - float(real[real_key])) / float(real[real_key])
|
||||
for real, sim in zip(real_rows, sim_rows)
|
||||
if real.get("success") and float(real[real_key]) != 0
|
||||
]
|
||||
output[metric] = summarize(errors)
|
||||
return output
|
||||
|
||||
|
||||
def aggregate_trial_bias(
|
||||
trial_biases: list[dict[str, dict[str, float]]],
|
||||
) -> dict[str, dict[str, dict[str, float]]]:
|
||||
return {
|
||||
metric: {
|
||||
quantile: {
|
||||
"mean": sum(values) / len(values),
|
||||
"min": min(values),
|
||||
"max": max(values),
|
||||
}
|
||||
for quantile in QUANTILES
|
||||
for values in [
|
||||
[trial[metric][quantile] for trial in trial_biases]
|
||||
]
|
||||
}
|
||||
for metric in METRICS
|
||||
}
|
||||
|
||||
|
||||
def legacy_pooled_bias(
|
||||
real_trials: list[list[dict[str, Any]]],
|
||||
sim_rows: list[dict[str, str]],
|
||||
) -> dict[str, dict[str, float]]:
|
||||
output: dict[str, dict[str, float]] = {}
|
||||
for metric, (real_key, sim_key) in METRICS.items():
|
||||
real_values = [
|
||||
float(row[real_key])
|
||||
for trial in real_trials
|
||||
for row in trial[: len(sim_rows)]
|
||||
if row.get("success")
|
||||
]
|
||||
sim_values = [float(row[sim_key]) for row in sim_rows]
|
||||
real_summary = summarize(real_values)
|
||||
sim_summary = summarize(sim_values)
|
||||
output[metric] = {
|
||||
name: (sim_summary[name] - real_summary[name]) / real_summary[name]
|
||||
for name in QUANTILES
|
||||
}
|
||||
return output
|
||||
|
||||
|
||||
def waiting_p99(sim_rows: list[dict[str, str]]) -> float:
|
||||
return percentile(
|
||||
[float(row["request_waiting_time_total"]) for row in sim_rows], 0.99
|
||||
)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
results: dict[str, Any] = {}
|
||||
flat_rows: list[dict[str, Any]] = []
|
||||
for label, paths in CELLS.items():
|
||||
real_trials = load_real_trials(paths["real"])
|
||||
old_sim = load_sim(paths["old"])
|
||||
new_sim = load_sim(ROOT / "replay" / label)
|
||||
old_trial_bias = [
|
||||
distribution_bias(trial, old_sim) for trial in real_trials
|
||||
]
|
||||
new_trial_bias = [
|
||||
distribution_bias(trial, new_sim) for trial in real_trials
|
||||
]
|
||||
old_legacy = legacy_pooled_bias(real_trials, old_sim)
|
||||
new_legacy = legacy_pooled_bias(real_trials, new_sim)
|
||||
wait_p99 = waiting_p99(new_sim)
|
||||
results[label] = {
|
||||
"old": {
|
||||
"trialwise_distribution_bias": old_trial_bias,
|
||||
"trialwise_distribution_bias_summary": aggregate_trial_bias(
|
||||
old_trial_bias
|
||||
),
|
||||
"legacy_pooled_distribution_bias": old_legacy,
|
||||
},
|
||||
"new": {
|
||||
"trialwise_distribution_bias": new_trial_bias,
|
||||
"trialwise_distribution_bias_summary": aggregate_trial_bias(
|
||||
new_trial_bias
|
||||
),
|
||||
"paired_relative_error": [
|
||||
paired_relative_error(trial, new_sim)
|
||||
for trial in real_trials
|
||||
],
|
||||
"legacy_pooled_distribution_bias": new_legacy,
|
||||
"waiting_p99_ms": wait_p99,
|
||||
"validity": (
|
||||
"PASS_SUBCRITICAL"
|
||||
if wait_p99 < 1000
|
||||
else "GATE_FAIL_DIAGNOSTIC"
|
||||
),
|
||||
},
|
||||
}
|
||||
for metric in METRICS:
|
||||
for quantile in QUANTILES:
|
||||
flat_rows.append(
|
||||
{
|
||||
"cell": label,
|
||||
"metric": metric,
|
||||
"quantile": quantile,
|
||||
"old_bias": old_legacy[metric][quantile],
|
||||
"new_bias": new_legacy[metric][quantile],
|
||||
"abs_bias_delta_pp": 100
|
||||
* (
|
||||
abs(new_legacy[metric][quantile])
|
||||
- abs(old_legacy[metric][quantile])
|
||||
),
|
||||
"validity": results[label]["new"]["validity"],
|
||||
}
|
||||
)
|
||||
|
||||
tp1_checks = []
|
||||
for cell in ("tp1_rho0p00125", "tp1_rho0p0025"):
|
||||
for quantile in ("mean", "p99"):
|
||||
old = results[cell]["old"]["legacy_pooled_distribution_bias"]["ttft"][
|
||||
quantile
|
||||
]
|
||||
new = results[cell]["new"]["legacy_pooled_distribution_bias"]["ttft"][
|
||||
quantile
|
||||
]
|
||||
tp1_checks.append(abs(old) - abs(new) >= 0.05)
|
||||
|
||||
regressions = [
|
||||
row
|
||||
for row in flat_rows
|
||||
if row["cell"].startswith(("tp2", "tp4"))
|
||||
and row["metric"] in ("ttft", "e2e")
|
||||
and row["abs_bias_delta_pp"] > 5
|
||||
]
|
||||
checks = {
|
||||
"tp1_ttft_mean_p99_improve_ge_5pp": all(tp1_checks),
|
||||
"tp2_tp4_ttft_e2e_no_abs_regression_gt_5pp": not regressions,
|
||||
"regressions": regressions,
|
||||
}
|
||||
checks["trace_gate"] = (
|
||||
checks["tp1_ttft_mean_p99_improve_ge_5pp"]
|
||||
and checks["tp2_tp4_ttft_e2e_no_abs_regression_gt_5pp"]
|
||||
)
|
||||
|
||||
payload = {
|
||||
"schema": "frontier-attn-structured-trial-aware-verdict-v1",
|
||||
"metric_note": (
|
||||
"Primary values are per-real-trial distribution biases with request "
|
||||
"alignment by index. legacy_pooled reproduces the old milestone "
|
||||
"quantile convention only for direct comparison."
|
||||
),
|
||||
"cells": results,
|
||||
"checks": checks,
|
||||
}
|
||||
output = ROOT / "results"
|
||||
output.mkdir(parents=True, exist_ok=True)
|
||||
(output / "trace-verdict.json").write_text(json.dumps(payload, indent=2))
|
||||
with (output / "trace-verdict.csv").open("w", newline="") as stream:
|
||||
writer = csv.DictWriter(stream, fieldnames=list(flat_rows[0]))
|
||||
writer.writeheader()
|
||||
writer.writerows(flat_rows)
|
||||
|
||||
print(json.dumps(checks, indent=2))
|
||||
for label, result in results.items():
|
||||
old = result["old"]["legacy_pooled_distribution_bias"]["ttft"]
|
||||
new = result["new"]["legacy_pooled_distribution_bias"]["ttft"]
|
||||
print(
|
||||
f"{label}: TTFT mean {old['mean']:+.1%}->{new['mean']:+.1%}, "
|
||||
f"p99 {old['p99']:+.1%}->{new['p99']:+.1%}, "
|
||||
f"waiting_p99={result['new']['waiting_p99_ms']:.0f}ms "
|
||||
f"{result['new']['validity']}"
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
82
runs/frontier-attn-structured-v0/experiment-card.md
Normal file
82
runs/frontier-attn-structured-v0/experiment-card.md
Normal file
@@ -0,0 +1,82 @@
|
||||
# 实验 EXP-ATTN-STRUCTURED：结构化 predictor 能否关闭大 KV 端的 RF 欠拟合
|
||||
|
||||
> **状态：** 已完成（profile gate PASS；global merge gate FAIL）
|
||||
>
|
||||
> Parent campaign：[`../frontier-simulator-gap-campaign-v0/README.md`](../frontier-simulator-gap-campaign-v0/README.md)
|
||||
|
||||
## Claim 与决策
|
||||
|
||||
- **Parent claim：** profile-v5 已补齐 chunked-prefill KV-context 测量，但当前 RF 仍在 TP1/2/4 的新网格上产生约 12%--14% self-fit MAPE，并在 TP1 真实 trace 中留下 −13% 到 −22% TTFT 偏差。
|
||||
- **目的：** 检查该 residual 是否来自可工程修复的 predictor representation，而不是 profile 数据或 serving path。
|
||||
- **Competing hypotheses：**
|
||||
- H1：standard prefill 模型错误混入 pure multi-request rows，且 RF 对连续 attention scaling 作阶梯平滑；使用单请求数据和结构化 `base(q)+KV×(a+bq)` 可关闭残余。
|
||||
- H2：残余主要来自未建模的 serving-path 组件；替换 predictor 不会改善 7-cell trace fidelity。
|
||||
- **事前预测：**
|
||||
- H1：held-out context MAPE ≤5%，TP1 TTFT mean/p99 绝对偏差至少改善 5 pp。
|
||||
- H2：profile gate 失败，或 profile gate 通过但 trace TTFT 几乎不动。
|
||||
- **判定规则：**
|
||||
- profile gate：TP1/2/4 held-out context MAPE 均 ≤5%；q/KV 单调且预测非负。
|
||||
- trace gate：两个 TP1 cell 的 TTFT mean/p99 |bias| 各改善 ≥5 pp；TP2/TP4 任一 TTFT/E2E quantile 不恶化 >5 pp。
|
||||
- profile gate 失败即停止；trace gate 失败则回退 patch，不进入 EXP-2。
|
||||
|
||||
## Setup
|
||||
|
||||
- **自变量：**
|
||||
- A：现有 RF，standard prefill 全部非 true-mixed rows。
|
||||
- B：现有 RF，但仅 `batch_size=1`。
|
||||
- C：仅 `batch_size=1` 的 structured predictor：
|
||||
- `base(q)`：KV=0 profile 的单调分段线性插值；
|
||||
- growth：非负 least-squares `KV×(a+bq)`。
|
||||
- **控制变量：** attention/linear/MoE/collective profile、trace、prefix cache、scheduler、graph mode、KV blocks、MNS、全部 argv。
|
||||
- **System context：** Qwen3-30B-A3B BF16；H20；Frontier `deadc4a3`；TP1/2/4；MNS16；chunk 8192；prefix caching。
|
||||
- **Workload 或 trace：** 现有 7-cell 60-min production chat trace matrix；real 侧每 cell 两个 trial。
|
||||
- **Baselines：** `docs/assets/frontier-fidelity/full-matrix.csv` 的 sim-v5。
|
||||
- **Metrics：**
|
||||
- profile：grid fit MAPE、leave-one-context MAPE/max error、q/KV monotonicity；
|
||||
- trace：request-ID paired bias；每个 real trial 单独计算后报告 mean 与 trial interval；
|
||||
- queue validity：waiting p99，TP1 超过 1 s 的 cell 标为 diagnostic。
|
||||
|
||||
## 预期产物与 review
|
||||
|
||||
- **预期数据：** `results/predictor-ablation.{json,csv}`、`replay/<cell>/`、`results/paired-verdict.json`。
|
||||
- **Figure prototype：** `figure-prototype.png`；左图为 q8k 随 KV 增长的 actual/RF/structured，右图为 7-cell TTFT bias 的事前期望。
|
||||
- **人工 review：** 已按 campaign 顺序批准执行。
|
||||
- **Review 意见：** 只改 standard single-request predictor；不得改 mixed predictor 或任何 profile row。
|
||||
|
||||
## 复现信息
|
||||
|
||||
- **Code：** Frontier base `deadc4a321f0baaa534c6ebd17f974123733cdc2`；实验 patch 将保存为 `frontier-structured-attn.patch` 并记录 SHA256。
|
||||
- **Environment：** 本地 CPU replay；Python dependency roots 复用 `runs/frontier-collective-joint-v0/counterfactual/joint-r2/manifest.json`。
|
||||
- **产物路径：** 本目录。
|
||||
- **已知 deviation：** milestone 文档将 7-cell 口径称为“逐 request paired”，但旧脚本实际 pool 两个 real trial 后比较 quantile；本实验会修正分析口径，不改旧结果文件。
|
||||
|
||||
## 预分析事实
|
||||
|
||||
- 现有训练代码使用 `["kv_cache_size", "prefill_chunk_size_squared"]` 与 RF grid search。
|
||||
- runtime cache 注释明确 standard model 是 per-request；多请求 prefill 在模型存在时走 `attn_prefill_mixed`。
|
||||
- profile-v5 的 standard 训练集每 TP 有 29 行，其中单请求 23 行；有 4 组相同 `(KV,q²)` feature 对应多个 pure-batch 标签。
|
||||
- 初步 structured candidate 的 leave-one-context MAPE：TP1 0.84%、TP2 1.61%、TP4 3.01%；max error 分别 2.04%、3.47%、5.49%。这些是实现前的临时计算，须由版本化脚本复现后才进入结果。
|
||||
|
||||
## 结果
|
||||
|
||||
- **观察事实：**
|
||||
- structured held-out-context MAPE 为 TP1/2/4=`0.84%/1.60%/3.01%`；
|
||||
当前 RF 为 `44.40%/44.20%/43.54%`。单调/非负 gate 通过。
|
||||
- TP1 两点 TTFT mean bias `−13.5/−17.7% → −6.3/−9.5%`，p99
|
||||
`−16.8/−22.1% → −8.6/−14.4%`。
|
||||
- TP2 两点 TTFT mean bias `−11.2/−14.1% → −4.5/−7.1%`，p99
|
||||
`−17.3/−19.4% → −7.7/−9.0%`。
|
||||
- TP4 三点 TTFT mean bias `+2.5/+2.9/−0.1% → +7.8/+8.4/+6.0%`；
|
||||
三点均使绝对误差恶化 `5.3--5.8 pp`，触发预设回归 gate。
|
||||
- validity 重新审计：TP1 两点 waiting p99=`1.34/1.89 s`；TP2
|
||||
ρ=.005=`1.17 s`，均标为 `GATE_FAIL_DIAGNOSTIC`。其余四点通过。
|
||||
- **异常：** TP4 ρ=.005 的 TPOT p99 从 `+31.2%` 变为 `+36.6%`，
|
||||
表明该 tail 对 prefill/mixed-decode 相位敏感，不是本 patch 能关闭的稳定
|
||||
decode predictor 偏差。
|
||||
- **含义：** H1 的 representation 机制得到支持，但“全局替换 RF 可直接提升
|
||||
7-cell fidelity”被反驳。TP4 原先接近零的 mean TTFT 含有 predictor
|
||||
欠拟合与其它正向 residual 的误差抵消；单独修正 attention 会揭开后者。
|
||||
- **Claim update：** structured predictor 是明确的工程候选，但必须与 TP4
|
||||
residual 联合收敛后才可 merge；当前 patch 只保留为 ablation。
|
||||
- **下一步：** EXP-2 先重算 structured 分支的 TP2 chunk-level residual；
|
||||
仅 residual ≥10% 才运行 GPU serving-path 三臂 profile。
|
||||
BIN
runs/frontier-attn-structured-v0/figure-prototype.png
Normal file
BIN
runs/frontier-attn-structured-v0/figure-prototype.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 119 KiB |
525
runs/frontier-attn-structured-v0/frontier-reference.json
Normal file
525
runs/frontier-attn-structured-v0/frontier-reference.json
Normal file
@@ -0,0 +1,525 @@
|
||||
{
|
||||
"cc_cache": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
||||
"cells": {
|
||||
"tp1_mns16": {
|
||||
"argv": [
|
||||
"/usr/bin/python3",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
||||
"--simulation_mode",
|
||||
"online",
|
||||
"--sys_arch",
|
||||
"co-location",
|
||||
"--cc_backend_config_type",
|
||||
"vidur",
|
||||
"--cluster_config_num_replicas",
|
||||
"1",
|
||||
"--cluster_scheduler_config_type",
|
||||
"sticky_round_robin",
|
||||
"--replica_config_model_name",
|
||||
"qwen3-a3b-30b-moe",
|
||||
"--replica_config_device",
|
||||
"h20",
|
||||
"--replica_config_network_device",
|
||||
"h20_dgx",
|
||||
"--replica_config_attn_tensor_parallel_size",
|
||||
"1",
|
||||
"--replica_config_attn_data_parallel_size",
|
||||
"1",
|
||||
"--replica_config_moe_tensor_parallel_size",
|
||||
"1",
|
||||
"--replica_config_moe_expert_parallel_size",
|
||||
"1",
|
||||
"--replica_config_num_pipeline_stages",
|
||||
"1",
|
||||
"--replica_scheduler_config_type",
|
||||
"vllm_v1",
|
||||
"--decode_cuda_graph_mode",
|
||||
"piecewise",
|
||||
"--vllm_v1_scheduler_config_batch_size_cap",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
||||
"8192",
|
||||
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
||||
"0",
|
||||
"--vllm_v1_scheduler_config_block_size",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_num_blocks_mode",
|
||||
"explicit",
|
||||
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
||||
"0.92",
|
||||
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
||||
"0",
|
||||
"--request_generator_config_type",
|
||||
"trace_replay",
|
||||
"--trace_request_generator_config_trace_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp1-frontier.csv",
|
||||
"--trace_request_generator_config_max_tokens",
|
||||
"40960",
|
||||
"--metrics_config_output_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp1_mns16/metrics",
|
||||
"--metrics_config_run_id",
|
||||
"joint_tp1_mns16",
|
||||
"--metrics_config_write_metrics",
|
||||
"--metrics_config_store_request_metrics",
|
||||
"--metrics_config_store_batch_metrics",
|
||||
"--metrics_config_store_token_completion_metrics",
|
||||
"--metrics_config_store_utilization_metrics",
|
||||
"--no-metrics_config_store_plots",
|
||||
"--no-metrics_config_enable_chrome_trace",
|
||||
"--no-metrics_config_write_json_trace",
|
||||
"--metrics_config_store_frontier_stage_batch_ledger",
|
||||
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
||||
"8192",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
||||
"32",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
||||
"40960",
|
||||
"--random_forrest_execution_time_predictor_config_no_cache",
|
||||
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
||||
"--vllm_v1_scheduler_config_num_blocks",
|
||||
"20128",
|
||||
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
||||
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
||||
"4",
|
||||
"--cudagraph_capture_sizes",
|
||||
"1",
|
||||
"2",
|
||||
"4",
|
||||
"8",
|
||||
"16",
|
||||
"24",
|
||||
"32",
|
||||
"--vidur_cc_backend_config_all_reduce_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
||||
"--vidur_cc_backend_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
||||
"--vidur_cc_backend_config_k_fold_cv_splits",
|
||||
"6",
|
||||
"--vidur_cc_backend_config_num_training_job_threads",
|
||||
"1",
|
||||
"--metrics_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
||||
],
|
||||
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp1_mns16.log",
|
||||
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp1_mns16/tp1/command.json",
|
||||
"source_command_sha256": "a9815797b1601bf6f6cdf0269e84acb376a84945609e338868dc8347aab650e6",
|
||||
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp1_mns16.json"
|
||||
},
|
||||
"tp2_mns16": {
|
||||
"argv": [
|
||||
"/usr/bin/python3",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
||||
"--simulation_mode",
|
||||
"online",
|
||||
"--sys_arch",
|
||||
"co-location",
|
||||
"--cc_backend_config_type",
|
||||
"vidur",
|
||||
"--cluster_config_num_replicas",
|
||||
"1",
|
||||
"--cluster_scheduler_config_type",
|
||||
"sticky_round_robin",
|
||||
"--replica_config_model_name",
|
||||
"qwen3-a3b-30b-moe",
|
||||
"--replica_config_device",
|
||||
"h20",
|
||||
"--replica_config_network_device",
|
||||
"h20_dgx",
|
||||
"--replica_config_attn_tensor_parallel_size",
|
||||
"2",
|
||||
"--replica_config_attn_data_parallel_size",
|
||||
"1",
|
||||
"--replica_config_moe_tensor_parallel_size",
|
||||
"2",
|
||||
"--replica_config_moe_expert_parallel_size",
|
||||
"1",
|
||||
"--replica_config_num_pipeline_stages",
|
||||
"1",
|
||||
"--replica_scheduler_config_type",
|
||||
"vllm_v1",
|
||||
"--decode_cuda_graph_mode",
|
||||
"piecewise",
|
||||
"--vllm_v1_scheduler_config_batch_size_cap",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
||||
"8192",
|
||||
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
||||
"0",
|
||||
"--vllm_v1_scheduler_config_block_size",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_num_blocks_mode",
|
||||
"explicit",
|
||||
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
||||
"0.92",
|
||||
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
||||
"0",
|
||||
"--request_generator_config_type",
|
||||
"trace_replay",
|
||||
"--trace_request_generator_config_trace_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp2-frontier.csv",
|
||||
"--trace_request_generator_config_max_tokens",
|
||||
"40960",
|
||||
"--metrics_config_output_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp2_mns16/metrics",
|
||||
"--metrics_config_run_id",
|
||||
"joint_tp2_mns16",
|
||||
"--metrics_config_write_metrics",
|
||||
"--metrics_config_store_request_metrics",
|
||||
"--metrics_config_store_batch_metrics",
|
||||
"--metrics_config_store_token_completion_metrics",
|
||||
"--metrics_config_store_utilization_metrics",
|
||||
"--no-metrics_config_store_plots",
|
||||
"--no-metrics_config_enable_chrome_trace",
|
||||
"--no-metrics_config_write_json_trace",
|
||||
"--metrics_config_store_frontier_stage_batch_ledger",
|
||||
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
||||
"8192",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
||||
"32",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
||||
"40960",
|
||||
"--random_forrest_execution_time_predictor_config_no_cache",
|
||||
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
||||
"--vllm_v1_scheduler_config_num_blocks",
|
||||
"76620",
|
||||
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
||||
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
||||
"4",
|
||||
"--cudagraph_capture_sizes",
|
||||
"1",
|
||||
"2",
|
||||
"4",
|
||||
"8",
|
||||
"16",
|
||||
"24",
|
||||
"32",
|
||||
"--vidur_cc_backend_config_all_reduce_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
||||
"--vidur_cc_backend_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
||||
"--vidur_cc_backend_config_k_fold_cv_splits",
|
||||
"6",
|
||||
"--vidur_cc_backend_config_num_training_job_threads",
|
||||
"1",
|
||||
"--metrics_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
||||
],
|
||||
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp2_mns16.log",
|
||||
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp2_mns16/tp2/command.json",
|
||||
"source_command_sha256": "61788a8810be301c9dbc006624aa19b6a932bc44d341b836861087833cffc3df",
|
||||
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp2_mns16.json"
|
||||
},
|
||||
"tp4_mns16": {
|
||||
"argv": [
|
||||
"/usr/bin/python3",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
||||
"--simulation_mode",
|
||||
"online",
|
||||
"--sys_arch",
|
||||
"co-location",
|
||||
"--cc_backend_config_type",
|
||||
"vidur",
|
||||
"--cluster_config_num_replicas",
|
||||
"1",
|
||||
"--cluster_scheduler_config_type",
|
||||
"sticky_round_robin",
|
||||
"--replica_config_model_name",
|
||||
"qwen3-a3b-30b-moe",
|
||||
"--replica_config_device",
|
||||
"h20",
|
||||
"--replica_config_network_device",
|
||||
"h20_dgx",
|
||||
"--replica_config_attn_tensor_parallel_size",
|
||||
"4",
|
||||
"--replica_config_attn_data_parallel_size",
|
||||
"1",
|
||||
"--replica_config_moe_tensor_parallel_size",
|
||||
"4",
|
||||
"--replica_config_moe_expert_parallel_size",
|
||||
"1",
|
||||
"--replica_config_num_pipeline_stages",
|
||||
"1",
|
||||
"--replica_scheduler_config_type",
|
||||
"vllm_v1",
|
||||
"--decode_cuda_graph_mode",
|
||||
"piecewise",
|
||||
"--vllm_v1_scheduler_config_batch_size_cap",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
||||
"8192",
|
||||
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
||||
"0",
|
||||
"--vllm_v1_scheduler_config_block_size",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_num_blocks_mode",
|
||||
"explicit",
|
||||
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
||||
"0.92",
|
||||
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
||||
"0",
|
||||
"--request_generator_config_type",
|
||||
"trace_replay",
|
||||
"--trace_request_generator_config_trace_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp4-frontier.csv",
|
||||
"--trace_request_generator_config_max_tokens",
|
||||
"40960",
|
||||
"--metrics_config_output_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp4_mns16/metrics",
|
||||
"--metrics_config_run_id",
|
||||
"joint_tp4_mns16",
|
||||
"--metrics_config_write_metrics",
|
||||
"--metrics_config_store_request_metrics",
|
||||
"--metrics_config_store_batch_metrics",
|
||||
"--metrics_config_store_token_completion_metrics",
|
||||
"--metrics_config_store_utilization_metrics",
|
||||
"--no-metrics_config_store_plots",
|
||||
"--no-metrics_config_enable_chrome_trace",
|
||||
"--no-metrics_config_write_json_trace",
|
||||
"--metrics_config_store_frontier_stage_batch_ledger",
|
||||
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
||||
"8192",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
||||
"32",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
||||
"40960",
|
||||
"--random_forrest_execution_time_predictor_config_no_cache",
|
||||
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
||||
"--vllm_v1_scheduler_config_num_blocks",
|
||||
"191882",
|
||||
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
||||
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
||||
"4",
|
||||
"--cudagraph_capture_sizes",
|
||||
"1",
|
||||
"2",
|
||||
"4",
|
||||
"8",
|
||||
"16",
|
||||
"24",
|
||||
"32",
|
||||
"--vidur_cc_backend_config_all_reduce_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
||||
"--vidur_cc_backend_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
||||
"--vidur_cc_backend_config_k_fold_cv_splits",
|
||||
"6",
|
||||
"--vidur_cc_backend_config_num_training_job_threads",
|
||||
"1",
|
||||
"--metrics_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
||||
],
|
||||
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp4_mns16.log",
|
||||
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp4_mns16/tp4/command.json",
|
||||
"source_command_sha256": "9bbcf10446336ba5885193f391dd628cd18ff64d91a51ebcd463ffd24be95532",
|
||||
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp4_mns16.json"
|
||||
},
|
||||
"tp4_mns32": {
|
||||
"argv": [
|
||||
"/usr/bin/python3",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
||||
"--simulation_mode",
|
||||
"online",
|
||||
"--sys_arch",
|
||||
"co-location",
|
||||
"--cc_backend_config_type",
|
||||
"vidur",
|
||||
"--cluster_config_num_replicas",
|
||||
"1",
|
||||
"--cluster_scheduler_config_type",
|
||||
"sticky_round_robin",
|
||||
"--replica_config_model_name",
|
||||
"qwen3-a3b-30b-moe",
|
||||
"--replica_config_device",
|
||||
"h20",
|
||||
"--replica_config_network_device",
|
||||
"h20_dgx",
|
||||
"--replica_config_attn_tensor_parallel_size",
|
||||
"4",
|
||||
"--replica_config_attn_data_parallel_size",
|
||||
"1",
|
||||
"--replica_config_moe_tensor_parallel_size",
|
||||
"4",
|
||||
"--replica_config_moe_expert_parallel_size",
|
||||
"1",
|
||||
"--replica_config_num_pipeline_stages",
|
||||
"1",
|
||||
"--replica_scheduler_config_type",
|
||||
"vllm_v1",
|
||||
"--decode_cuda_graph_mode",
|
||||
"piecewise",
|
||||
"--vllm_v1_scheduler_config_batch_size_cap",
|
||||
"32",
|
||||
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
||||
"8192",
|
||||
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
||||
"0",
|
||||
"--vllm_v1_scheduler_config_block_size",
|
||||
"16",
|
||||
"--vllm_v1_scheduler_config_num_blocks_mode",
|
||||
"explicit",
|
||||
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
||||
"0.92",
|
||||
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
||||
"0",
|
||||
"--request_generator_config_type",
|
||||
"trace_replay",
|
||||
"--trace_request_generator_config_trace_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp4-frontier.csv",
|
||||
"--trace_request_generator_config_max_tokens",
|
||||
"40960",
|
||||
"--metrics_config_output_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp4_mns32/metrics",
|
||||
"--metrics_config_run_id",
|
||||
"joint_tp4_mns32",
|
||||
"--metrics_config_write_metrics",
|
||||
"--metrics_config_store_request_metrics",
|
||||
"--metrics_config_store_batch_metrics",
|
||||
"--metrics_config_store_token_completion_metrics",
|
||||
"--metrics_config_store_utilization_metrics",
|
||||
"--no-metrics_config_store_plots",
|
||||
"--no-metrics_config_enable_chrome_trace",
|
||||
"--no-metrics_config_write_json_trace",
|
||||
"--metrics_config_store_frontier_stage_batch_ledger",
|
||||
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
||||
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
||||
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
||||
"8192",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
||||
"64",
|
||||
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
||||
"40960",
|
||||
"--random_forrest_execution_time_predictor_config_no_cache",
|
||||
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
||||
"--vllm_v1_scheduler_config_num_blocks",
|
||||
"191786",
|
||||
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
||||
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
||||
"4",
|
||||
"--cudagraph_capture_sizes",
|
||||
"1",
|
||||
"2",
|
||||
"4",
|
||||
"8",
|
||||
"16",
|
||||
"24",
|
||||
"32",
|
||||
"40",
|
||||
"48",
|
||||
"56",
|
||||
"64",
|
||||
"--vidur_cc_backend_config_all_reduce_input_file",
|
||||
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
||||
"--vidur_cc_backend_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
||||
"--vidur_cc_backend_config_k_fold_cv_splits",
|
||||
"6",
|
||||
"--vidur_cc_backend_config_num_training_job_threads",
|
||||
"1",
|
||||
"--metrics_config_cache_dir",
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
||||
],
|
||||
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp4_mns32.log",
|
||||
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp4_mns32/tp4/command.json",
|
||||
"source_command_sha256": "fbc7dee55590b415ed1cde8072de835ed155a0c20ba0eb305c3cb22aa8065a51",
|
||||
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp4_mns32.json"
|
||||
}
|
||||
},
|
||||
"collective_curve": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/results/collective-curve.json",
|
||||
"collective_curve_sha256": "f9543649d4ea78f08240bf1284ab74083aa5cf5671ed47e386047f1453300b36",
|
||||
"collective_curve_variant": "drop_mean",
|
||||
"frontier_checkout": "/tmp/frontier-attn-structured-v0",
|
||||
"frontier_commit": "1f8900a4ac64e45754b03d0aa7c1dddab65785cf",
|
||||
"mode": "joint",
|
||||
"model_cache": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache",
|
||||
"moe_curve": "/home/gahow/phd/aituner/runs/frontier-fused-moe-profile-v0/results/fused-moe-curve.json",
|
||||
"moe_curve_sha256": "b94d65d9d581adefcc6c14ed4920cce6a1136f74f1014737dc3e4249bc8250d2",
|
||||
"python": "/usr/bin/python3",
|
||||
"python_dependency_roots": [
|
||||
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/python-deps",
|
||||
"/home/gahow/.cache/uv/archive-v0/-_kzErLcPO5nASZFX8b9k",
|
||||
"/home/gahow/.cache/uv/archive-v0/FbaBs_QJ9QKEbQ9V_4aIR",
|
||||
"/home/gahow/.cache/uv/archive-v0/fuHsGXD0Lv_UjFC8yI4-7",
|
||||
"/home/gahow/.cache/uv/archive-v0/jFGdqQLpB1eopfm9VxT3j",
|
||||
"/home/gahow/.cache/uv/archive-v0/YWW6ExSJuPVvv4-qYQTin",
|
||||
"/home/gahow/.cache/uv/archive-v0/3_qxZ5Ll-EpVAGZfbksfe"
|
||||
],
|
||||
"traces": {
|
||||
"1": {
|
||||
"first_arrival_s": 0.0,
|
||||
"last_arrival_s": 595.348837209302,
|
||||
"requests": 129,
|
||||
"source_request_metrics": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp1_mns16/tp1/metrics/qwen3_a3b_30b_moe/online_serving/qwen30_trace_tp1_mns16_tp1/request_metrics.csv",
|
||||
"source_sha256": "0b82e09644a5884fcd10d894b68495daefdabb32b770146c2f9ece37b8469f4f",
|
||||
"trace": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp1-frontier.csv",
|
||||
"trace_sha256": "59dd8996ff879ef94330004104dfdf515b791bce4036576eccc93290e9206dad"
|
||||
},
|
||||
"2": {
|
||||
"first_arrival_s": 0.0,
|
||||
"last_arrival_s": 297.674418604651,
|
||||
"requests": 129,
|
||||
"source_request_metrics": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp2_mns16/tp2/metrics/qwen3_a3b_30b_moe/online_serving/qwen30_trace_tp2_mns16_tp2/request_metrics.csv",
|
||||
"source_sha256": "33983081bb20dd5e2053e9e3d13def8732e958150c9b47a8609ba345123f2316",
|
||||
"trace": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp2-frontier.csv",
|
||||
"trace_sha256": "64fc077b38274a76a8279884ac4115836cd1157c95119c64fabac50d81124f69"
|
||||
},
|
||||
"4": {
|
||||
"first_arrival_s": 0.0,
|
||||
"last_arrival_s": 148.837209302326,
|
||||
"requests": 129,
|
||||
"source_request_metrics": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp4_mns16/tp4/metrics/qwen3_a3b_30b_moe/online_serving/qwen30_trace_tp4_mns16_tp4/request_metrics.csv",
|
||||
"source_sha256": "b36cd383c07b546d2c1f2fac754d5dbb92efd6880316b4233a7aef9fa1115a36",
|
||||
"trace": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp4-frontier.csv",
|
||||
"trace_sha256": "adb3d6f3932a44c86c3d9e7cf1e57739594e8c48d19a26b5aa54b37dce0e0c19"
|
||||
}
|
||||
}
|
||||
}
|
||||
72
runs/frontier-attn-structured-v0/plot_figure_prototype.py
Normal file
72
runs/frontier-attn-structured-v0/plot_figure_prototype.py
Normal file
@@ -0,0 +1,72 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Schematic figure frozen before EXP-ATTN-STRUCTURED execution."""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
import matplotlib
|
||||
|
||||
matplotlib.use("Agg")
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
|
||||
ROOT = Path(__file__).resolve().parent
|
||||
SURFACE = "#fcfcfb"
|
||||
INK = "#111111"
|
||||
MUTED = "#77736c"
|
||||
GRID = "#dedbd2"
|
||||
RF = "#d95f02"
|
||||
STRUCTURED = "#1b75bc"
|
||||
|
||||
fig, axes = plt.subplots(1, 2, figsize=(10.8, 4.2), dpi=160)
|
||||
fig.patch.set_facecolor(SURFACE)
|
||||
|
||||
for ax in axes:
|
||||
ax.set_facecolor(SURFACE)
|
||||
ax.grid(axis="y", color=GRID, linewidth=0.8)
|
||||
ax.set_axisbelow(True)
|
||||
ax.spines[["top", "right"]].set_visible(False)
|
||||
ax.tick_params(colors=MUTED, labelsize=8)
|
||||
|
||||
kv = np.array([8, 16, 24], dtype=float)
|
||||
actual = np.array([11.97, 19.92, 27.84])
|
||||
rf = np.array([9.46, 16.40, 24.52])
|
||||
structured_expected = np.array([12.0, 19.9, 27.9])
|
||||
axes[0].plot(kv, actual, "o-", color=INK, label="profile actual")
|
||||
axes[0].plot(kv, rf, "s--", color=RF, label="current RF")
|
||||
axes[0].plot(
|
||||
kv,
|
||||
structured_expected,
|
||||
"^:",
|
||||
color=STRUCTURED,
|
||||
label="structured (expected)",
|
||||
)
|
||||
axes[0].set_xlabel("KV context (ktok)")
|
||||
axes[0].set_ylabel("TP1 q8k attention time (ms)")
|
||||
axes[0].set_title("(a) Continuous KV growth", loc="left", fontsize=10)
|
||||
axes[0].legend(frameon=False, fontsize=8)
|
||||
|
||||
labels = ["TP1\n.00125", "TP1\n.0025", "TP2\n.0025", "TP2\n.005",
|
||||
"TP4\n.0025", "TP4\n.005", "TP4\n.01"]
|
||||
x = np.arange(len(labels))
|
||||
v5_mean = np.array([-13.5, -17.7, -11.2, -14.1, 2.5, 2.9, -0.2])
|
||||
expected = np.array([-5, -8, -9, -11, 3, 3, 0])
|
||||
axes[1].axhspan(-15, 15, color=GRID, alpha=0.5)
|
||||
axes[1].axhline(0, color=MUTED, linewidth=0.8)
|
||||
axes[1].plot(x, v5_mean, "o-", color=RF, label="sim-v5 measured")
|
||||
axes[1].plot(x, expected, "s--", color=STRUCTURED, label="H1 expected")
|
||||
axes[1].set_xticks(x, labels)
|
||||
axes[1].set_ylabel("TTFT mean bias (%)")
|
||||
axes[1].set_title("(b) 7-cell trace gate", loc="left", fontsize=10)
|
||||
axes[1].legend(frameon=False, fontsize=8)
|
||||
|
||||
fig.suptitle(
|
||||
"MOCK / schematic — EXP-ATTN-STRUCTURED (not measured results)",
|
||||
x=0.01,
|
||||
ha="left",
|
||||
color=RF,
|
||||
fontsize=9,
|
||||
)
|
||||
fig.tight_layout(rect=(0, 0, 1, 0.95))
|
||||
fig.savefig(ROOT / "figure-prototype.png", facecolor=SURFACE)
|
||||
fig.savefig(ROOT / "figure-prototype.svg", facecolor=SURFACE)
|
||||
print(ROOT / "figure-prototype.png")
|
||||
@@ -0,0 +1,10 @@
|
||||
candidate,training_rows,grid_fit_mape_pct,single_fit_mape_pct,heldout_context_mape_pct,heldout_context_max_abs_error_pct,prediction_min_ms,q_min_delta_ms,kv_min_delta_ms,monotone_and_nonnegative,tp
|
||||
rf_all,29,15.074275515235467,19.842994757611535,44.40139318281943,82.78279487156401,0.06029164119272453,0.0,-4.2841601371801374e-05,False,1
|
||||
rf_single,23,11.834992526698676,22.893412972496023,34.45356428541224,62.49334437588834,0.059327708247725125,-0.00022153525203457564,-1.4336001873005433e-05,False,1
|
||||
structured_single,23,0.8432511364168856,2.227110646811972,0.841926169535806,2.0408978739639134,0.05679146709541477,0.0,0.0016745062683911627,True,1
|
||||
rf_all,29,13.812689689573157,17.879870012606048,44.20143320278334,82.0656368501208,0.06000113548192927,-0.004361070463210395,-0.009949388915300408,False,2
|
||||
rf_single,23,10.738962684891058,20.818820413545826,34.84360402100271,66.67253880294443,0.059971319361210015,-0.003811210796127021,-0.009949388915300408,False,2
|
||||
structured_single,23,1.518412258922364,6.226292654776418,1.6047958673086566,3.464671475193195,0.05767893331746252,0.0,0.0013929374121726124,True,2
|
||||
rf_all,29,14.117015331381916,15.49366794487052,43.53650868837558,81.33508178007524,0.05866772018640992,-0.0009967416035880083,-5.5955198407176e-05,False,4
|
||||
rf_single,23,12.07517666989496,17.672692652721008,34.14562332866605,62.31478818862995,0.058213693721655094,-0.0012244979345549661,-8.259841203689389e-05,False,4
|
||||
structured_single,23,3.088740104976349,5.969109476280061,3.0103379904473164,5.490598706238697,0.05747733327249683,0.0,0.0012048051417407057,True,4
|
||||
|
149
runs/frontier-attn-structured-v0/results/predictor-ablation.json
Normal file
149
runs/frontier-attn-structured-v0/results/predictor-ablation.json
Normal file
@@ -0,0 +1,149 @@
|
||||
{
|
||||
"schema": "frontier-attn-structured-ablation-v1",
|
||||
"profile": "/home/gahow/phd/aituner/runs/frontier-prefill-kvgrowth-fix-v0/profiles/profile-v5-kvgrowth/attention.csv",
|
||||
"frontier_checkout": "/tmp/frontier-attn-structured-v0",
|
||||
"data_audit": {
|
||||
"tp1": {
|
||||
"standard_rows": 29,
|
||||
"single_request_rows": 23,
|
||||
"target_grid_rows": 10,
|
||||
"duplicate_feature_groups": 4
|
||||
},
|
||||
"tp2": {
|
||||
"standard_rows": 29,
|
||||
"single_request_rows": 23,
|
||||
"target_grid_rows": 10,
|
||||
"duplicate_feature_groups": 4
|
||||
},
|
||||
"tp4": {
|
||||
"standard_rows": 29,
|
||||
"single_request_rows": 23,
|
||||
"target_grid_rows": 10,
|
||||
"duplicate_feature_groups": 4
|
||||
}
|
||||
},
|
||||
"results": [
|
||||
{
|
||||
"candidate": "rf_all",
|
||||
"training_rows": 29,
|
||||
"grid_fit_mape_pct": 15.074275515235467,
|
||||
"single_fit_mape_pct": 19.842994757611535,
|
||||
"heldout_context_mape_pct": 44.40139318281943,
|
||||
"heldout_context_max_abs_error_pct": 82.78279487156401,
|
||||
"prediction_min_ms": 0.06029164119272453,
|
||||
"q_min_delta_ms": 0.0,
|
||||
"kv_min_delta_ms": -4.2841601371801374e-05,
|
||||
"monotone_and_nonnegative": false,
|
||||
"tp": 1
|
||||
},
|
||||
{
|
||||
"candidate": "rf_single",
|
||||
"training_rows": 23,
|
||||
"grid_fit_mape_pct": 11.834992526698676,
|
||||
"single_fit_mape_pct": 22.893412972496023,
|
||||
"heldout_context_mape_pct": 34.45356428541224,
|
||||
"heldout_context_max_abs_error_pct": 62.49334437588834,
|
||||
"prediction_min_ms": 0.059327708247725125,
|
||||
"q_min_delta_ms": -0.00022153525203457564,
|
||||
"kv_min_delta_ms": -1.4336001873005433e-05,
|
||||
"monotone_and_nonnegative": false,
|
||||
"tp": 1
|
||||
},
|
||||
{
|
||||
"candidate": "structured_single",
|
||||
"training_rows": 23,
|
||||
"grid_fit_mape_pct": 0.8432511364168856,
|
||||
"single_fit_mape_pct": 2.227110646811972,
|
||||
"heldout_context_mape_pct": 0.841926169535806,
|
||||
"heldout_context_max_abs_error_pct": 2.0408978739639134,
|
||||
"prediction_min_ms": 0.05679146709541477,
|
||||
"q_min_delta_ms": 0.0,
|
||||
"kv_min_delta_ms": 0.0016745062683911627,
|
||||
"monotone_and_nonnegative": true,
|
||||
"tp": 1
|
||||
},
|
||||
{
|
||||
"candidate": "rf_all",
|
||||
"training_rows": 29,
|
||||
"grid_fit_mape_pct": 13.812689689573157,
|
||||
"single_fit_mape_pct": 17.879870012606048,
|
||||
"heldout_context_mape_pct": 44.20143320278334,
|
||||
"heldout_context_max_abs_error_pct": 82.0656368501208,
|
||||
"prediction_min_ms": 0.06000113548192927,
|
||||
"q_min_delta_ms": -0.004361070463210395,
|
||||
"kv_min_delta_ms": -0.009949388915300408,
|
||||
"monotone_and_nonnegative": false,
|
||||
"tp": 2
|
||||
},
|
||||
{
|
||||
"candidate": "rf_single",
|
||||
"training_rows": 23,
|
||||
"grid_fit_mape_pct": 10.738962684891058,
|
||||
"single_fit_mape_pct": 20.818820413545826,
|
||||
"heldout_context_mape_pct": 34.84360402100271,
|
||||
"heldout_context_max_abs_error_pct": 66.67253880294443,
|
||||
"prediction_min_ms": 0.059971319361210015,
|
||||
"q_min_delta_ms": -0.003811210796127021,
|
||||
"kv_min_delta_ms": -0.009949388915300408,
|
||||
"monotone_and_nonnegative": false,
|
||||
"tp": 2
|
||||
},
|
||||
{
|
||||
"candidate": "structured_single",
|
||||
"training_rows": 23,
|
||||
"grid_fit_mape_pct": 1.518412258922364,
|
||||
"single_fit_mape_pct": 6.226292654776418,
|
||||
"heldout_context_mape_pct": 1.6047958673086566,
|
||||
"heldout_context_max_abs_error_pct": 3.464671475193195,
|
||||
"prediction_min_ms": 0.05767893331746252,
|
||||
"q_min_delta_ms": 0.0,
|
||||
"kv_min_delta_ms": 0.0013929374121726124,
|
||||
"monotone_and_nonnegative": true,
|
||||
"tp": 2
|
||||
},
|
||||
{
|
||||
"candidate": "rf_all",
|
||||
"training_rows": 29,
|
||||
"grid_fit_mape_pct": 14.117015331381916,
|
||||
"single_fit_mape_pct": 15.49366794487052,
|
||||
"heldout_context_mape_pct": 43.53650868837558,
|
||||
"heldout_context_max_abs_error_pct": 81.33508178007524,
|
||||
"prediction_min_ms": 0.05866772018640992,
|
||||
"q_min_delta_ms": -0.0009967416035880083,
|
||||
"kv_min_delta_ms": -5.5955198407176e-05,
|
||||
"monotone_and_nonnegative": false,
|
||||
"tp": 4
|
||||
},
|
||||
{
|
||||
"candidate": "rf_single",
|
||||
"training_rows": 23,
|
||||
"grid_fit_mape_pct": 12.07517666989496,
|
||||
"single_fit_mape_pct": 17.672692652721008,
|
||||
"heldout_context_mape_pct": 34.14562332866605,
|
||||
"heldout_context_max_abs_error_pct": 62.31478818862995,
|
||||
"prediction_min_ms": 0.058213693721655094,
|
||||
"q_min_delta_ms": -0.0012244979345549661,
|
||||
"kv_min_delta_ms": -8.259841203689389e-05,
|
||||
"monotone_and_nonnegative": false,
|
||||
"tp": 4
|
||||
},
|
||||
{
|
||||
"candidate": "structured_single",
|
||||
"training_rows": 23,
|
||||
"grid_fit_mape_pct": 3.088740104976349,
|
||||
"single_fit_mape_pct": 5.969109476280061,
|
||||
"heldout_context_mape_pct": 3.0103379904473164,
|
||||
"heldout_context_max_abs_error_pct": 5.490598706238697,
|
||||
"prediction_min_ms": 0.05747733327249683,
|
||||
"q_min_delta_ms": 0.0,
|
||||
"kv_min_delta_ms": 0.0012048051417407057,
|
||||
"monotone_and_nonnegative": true,
|
||||
"tp": 4
|
||||
}
|
||||
],
|
||||
"checks": {
|
||||
"heldout_context_mape_le_5pct": true,
|
||||
"monotone_and_nonnegative": true,
|
||||
"profile_gate": true
|
||||
}
|
||||
}
|
||||
85
runs/frontier-attn-structured-v0/results/trace-verdict.csv
Normal file
85
runs/frontier-attn-structured-v0/results/trace-verdict.csv
Normal file
@@ -0,0 +1,85 @@
|
||||
cell,metric,quantile,old_bias,new_bias,abs_bias_delta_pp,validity
|
||||
tp1_rho0p00125,ttft,mean,-0.13461915993830945,-0.06328385143753473,-7.133530850077471,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,ttft,p50,-0.1888032883165517,-0.1117698463137391,-7.7033442002812595,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,ttft,p90,-0.23223319000679374,-0.0884727580604037,-14.376043194639005,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,ttft,p99,-0.16824856840168442,-0.08585570369326061,-8.239286470842382,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,tpot,mean,0.1305653876178269,0.14303898259628217,1.2473594978455265,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,tpot,p50,0.16837991778063455,0.1688780144991309,0.04980967184963492,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,tpot,p90,0.012855564422932954,0.02293841255516459,1.0082848132231637,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,tpot,p99,-0.08151080694091946,-0.06480973978913974,-1.6701067151779714,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,e2e,mean,0.06539157436639341,0.0838094906426525,1.8417916276259092,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,e2e,p50,0.10867934171755954,0.11142188099086506,0.2742539273305519,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,e2e,p90,0.10946179160934073,0.11872607178176105,0.9264280172420314,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p00125,e2e,p99,-0.0657146472433028,-0.04585643943465822,-1.9858207808644577,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,ttft,mean,-0.17677087458166194,-0.09487906467830536,-8.189180990335657,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,ttft,p50,0.008311436147272566,0.015508635458377175,0.7197199311104608,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,ttft,p90,-0.2608553178054708,-0.129865645852306,-13.098967195316478,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,ttft,p99,-0.22116442296103195,-0.14410151018893788,-7.706291277209407,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,tpot,mean,0.014380733682430142,0.052302860177306544,3.7922126494876403,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,tpot,p50,0.13351145963877706,0.14244154194999165,0.8930082311214588,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,tpot,p90,-0.05456950130438105,0.018069551387063856,-3.649994991731719,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,tpot,p99,-0.23635406197836167,-0.1790206784227079,-5.733338355565376,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,e2e,mean,-0.020164189983441452,0.01563919326555167,-0.4524996717889782,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,e2e,p50,0.07632815851795742,0.10505951594320918,2.8731357425251765,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,e2e,p90,0.049809009042946335,0.08165607475145953,3.1847065708513194,GATE_FAIL_DIAGNOSTIC
|
||||
tp1_rho0p0025,e2e,p99,-0.18303183751478602,-0.15333409130015813,-2.96977462146279,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p0025,ttft,mean,-0.11161154024124531,-0.045433491316312524,-6.617804892493279,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,ttft,p50,-0.18420934047220774,-0.0875990583320057,-9.661028214020204,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,ttft,p90,-0.21836264490202395,-0.1142200855839675,-10.414255931805645,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,ttft,p99,-0.17283197594971011,-0.07674087497700505,-9.609110097270507,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,tpot,mean,0.13711499081487563,0.15073709978689778,1.362210897202215,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,tpot,p50,0.17555321305308488,0.18527285925405948,0.9719646200974597,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,tpot,p90,0.0591579975137338,0.07863996768588354,1.9481970172149734,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,tpot,p99,0.1300483675091633,0.1661995397125918,3.6151172203428503,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,e2e,mean,0.10925353865257875,0.12696146154030977,1.7707922887731016,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,e2e,p50,0.1339165600755408,0.14796251184179712,1.404595176625631,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,e2e,p90,0.10666828724664539,0.12767235986604622,2.1004072619400835,PASS_SUBCRITICAL
|
||||
tp2_rho0p0025,e2e,p99,-0.07437942975605877,-0.03965040123988098,-3.472902851617779,PASS_SUBCRITICAL
|
||||
tp2_rho0p005,ttft,mean,-0.14129871969878843,-0.07082500585057615,-7.047371384821228,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,ttft,p50,-0.2042045530944649,-0.1284088888361358,-7.579566425832909,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,ttft,p90,-0.19003454588767263,-0.111136573344055,-7.889797254361763,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,ttft,p99,-0.19373351009539902,-0.09012556161973535,-10.360794847566366,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,tpot,mean,0.03117337438562004,0.05457336599027876,2.3399991604658723,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,tpot,p50,0.07668249597302182,0.0872512146277895,1.0568718654767675,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,tpot,p90,-0.03724827658429621,0.01132352325010614,-2.5924753334190074,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,tpot,p99,-0.10050436157089844,-0.05948329733667248,-4.102106423422596,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,e2e,mean,0.023867807624916495,0.050164236759908075,2.629642913499158,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,e2e,p50,0.07536668131278851,0.0912493994395978,1.588271812680929,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,e2e,p90,-0.03100470462321266,-0.0004979191794830456,-3.0506785443729614,GATE_FAIL_DIAGNOSTIC
|
||||
tp2_rho0p005,e2e,p99,-0.04909581632382212,-0.0014369075488634014,-4.765890877495872,GATE_FAIL_DIAGNOSTIC
|
||||
tp4_rho0p0025,ttft,mean,0.025022574738277282,0.07766646565061346,5.2643890912336175,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,ttft,p50,-0.040042171846277425,0.029153379043297147,-1.0888792802980278,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,ttft,p90,-0.056230097634382616,0.025222989748299444,-3.100710788608317,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,ttft,p99,-0.07535478089127973,0.0205549324689376,-5.479984842234213,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,tpot,mean,0.2170232618103144,0.2295170016795841,1.2493739869269715,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,tpot,p50,0.22406751004936917,0.22406940610958842,0.00018960602192474862,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,tpot,p90,0.1725668492041552,0.1795965483385546,0.7029699134399409,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,tpot,p99,0.1603764334794579,0.254199450927048,9.382301744759008,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,e2e,mean,0.18328079455378776,0.19190660476104554,0.8625810207257778,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,e2e,p50,0.2057109615696404,0.21253242300694286,0.6821461437302473,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,e2e,p90,0.1869703879211648,0.19279855916666536,0.5828171245500557,PASS_SUBCRITICAL
|
||||
tp4_rho0p0025,e2e,p99,0.14838304065885655,0.15160588346499027,0.3222842806133719,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,ttft,mean,0.028648879997638963,0.08356973519379125,5.492085519615229,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,ttft,p50,0.028237979190582876,0.09021324737193111,6.197526818134823,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,ttft,p90,-0.055961238578361966,-0.0006012940489499138,-5.535994452941205,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,ttft,p99,-0.045491187615110146,0.05253708684194205,0.7045899226831902,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,tpot,mean,0.1707193936623511,0.1813506819061229,1.0631288243771824,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,tpot,p50,0.16851374859025317,0.1743324539248605,0.5818705334607321,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,tpot,p90,0.10492621353626864,0.11816822907155744,1.3242015535288796,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,tpot,p99,0.31231888769471766,0.3662267201704473,5.390783247572961,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,e2e,mean,0.151102823467785,0.1630793421767109,1.197651870892591,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,e2e,p50,0.1594213531394918,0.17360527090575292,1.418391776626113,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,e2e,p90,0.1266352410718406,0.13652104764058856,0.9885806568747962,PASS_SUBCRITICAL
|
||||
tp4_rho0p005,e2e,p99,0.15576537699445703,0.17677450343779522,2.100912644333819,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,ttft,mean,-0.0014652143973501086,0.059650620031540064,5.8185405634189955,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,ttft,p50,0.22936601881498542,0.24159106387124998,1.2225045056264565,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,ttft,p90,-0.0646093465409875,-0.011548419893895705,-5.30609266470918,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,ttft,p99,-0.09621678853313553,-0.015475807392170575,-8.074098114096495,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,tpot,mean,0.06675609059150077,0.10596101263201793,3.9204922040517163,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,tpot,p50,0.08477302587551214,0.09703754188844527,1.2264516012933129,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,tpot,p90,0.0379183273767328,0.08369800201750718,4.577967464077439,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,tpot,p99,-0.010663954751357074,0.06667813160571406,5.601417685435699,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,e2e,mean,0.07212904317306096,0.09777288053702092,2.564383736395996,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,e2e,p50,0.12069215463307655,0.1388377217196832,1.8145567086606653,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,e2e,p90,0.03317293927357903,0.058060760567474216,2.4887821293895183,PASS_SUBCRITICAL
|
||||
tp4_rho0p01,e2e,p99,0.0338378271163308,0.06380410696893425,2.996627985260345,PASS_SUBCRITICAL
|
||||
|
2219
runs/frontier-attn-structured-v0/results/trace-verdict.json
Normal file
2219
runs/frontier-attn-structured-v0/results/trace-verdict.json
Normal file
File diff suppressed because it is too large
Load Diff
126
runs/frontier-attn-structured-v0/run_replay.py
Normal file
126
runs/frontier-attn-structured-v0/run_replay.py
Normal file
@@ -0,0 +1,126 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Replay one real-trace cell with the structured-attention experiment commit."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import importlib.util
|
||||
import json
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parent
|
||||
REPO = ROOT.parents[1]
|
||||
S3_REAL = REPO / "runs/frontier-s3-real-v0"
|
||||
BASE_REFERENCE = (
|
||||
REPO
|
||||
/ "runs/frontier-collective-joint-v0/counterfactual/joint-r2/manifest.json"
|
||||
)
|
||||
BASE_COMMIT = "deadc4a321f0baaa534c6ebd17f974123733cdc2"
|
||||
EXPERIMENT_COMMIT = "1f8900a4ac64e45754b03d0aa7c1dddab65785cf"
|
||||
PATCH = ROOT / "0001-Experiment-with-structured-attention-prefill-predict.patch"
|
||||
|
||||
|
||||
def load_s3_module():
|
||||
spec = importlib.util.spec_from_file_location(
|
||||
"s3_prefix_replay", S3_REAL / "run_frontier_prefix_replay.py"
|
||||
)
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
sys.path.insert(0, str(S3_REAL))
|
||||
spec.loader.exec_module(module)
|
||||
return module
|
||||
|
||||
|
||||
def git(checkout: Path, *args: str) -> str:
|
||||
return subprocess.check_output(
|
||||
["git", "-C", str(checkout), *args], text=True
|
||||
).strip()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--trace", type=Path, required=True)
|
||||
parser.add_argument("--output-root", type=Path, required=True)
|
||||
parser.add_argument(
|
||||
"--config",
|
||||
choices=("tp4_mns16", "tp2_mns16", "tp1_mns16"),
|
||||
required=True,
|
||||
)
|
||||
parser.add_argument("--label", required=True)
|
||||
parser.add_argument("--max-tokens", type=int, required=True)
|
||||
parser.add_argument("--duration-s", type=float)
|
||||
parser.add_argument("--cache-root", type=Path, required=True)
|
||||
parser.add_argument(
|
||||
"--frontier-checkout",
|
||||
type=Path,
|
||||
default=Path("/tmp/frontier-attn-structured-v0"),
|
||||
)
|
||||
parser.add_argument(
|
||||
"--attention-profile",
|
||||
type=Path,
|
||||
default=REPO
|
||||
/ "runs/frontier-prefill-kvgrowth-fix-v0/profiles/"
|
||||
"profile-v5-kvgrowth/attention.csv",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
frontier = args.frontier_checkout.resolve()
|
||||
profile = args.attention_profile.resolve()
|
||||
if git(frontier, "rev-parse", "HEAD") != EXPERIMENT_COMMIT:
|
||||
raise SystemExit(f"unexpected experiment checkout HEAD: {frontier}")
|
||||
if git(frontier, "rev-parse", "HEAD^") != BASE_COMMIT:
|
||||
raise SystemExit("experiment commit is not directly based on frozen Frontier")
|
||||
if git(frontier, "status", "--porcelain"):
|
||||
raise SystemExit("experiment Frontier checkout must be clean")
|
||||
if not profile.is_file():
|
||||
raise SystemExit(f"attention profile missing: {profile}")
|
||||
|
||||
reference = json.loads(BASE_REFERENCE.read_text())
|
||||
reference["frontier_checkout"] = str(frontier)
|
||||
reference["frontier_commit"] = EXPERIMENT_COMMIT
|
||||
generated_reference = ROOT / "frontier-reference.json"
|
||||
generated_reference.write_text(json.dumps(reference, indent=2))
|
||||
|
||||
module = load_s3_module()
|
||||
module.REFERENCE = generated_reference
|
||||
module.EXPECTED_FRONTIER_COMMIT = EXPERIMENT_COMMIT
|
||||
original_replace = module.replace_flag
|
||||
|
||||
def replace_and_override(argv: list[str], flag: str, value: str) -> None:
|
||||
original_replace(argv, flag, value)
|
||||
if flag.endswith("trace_file"):
|
||||
atten_flag = (
|
||||
"--random_forrest_execution_time_predictor_config_atten_input_file"
|
||||
)
|
||||
original_replace(argv, atten_flag, str(profile))
|
||||
no_cache = (
|
||||
"--random_forrest_execution_time_predictor_config_no_cache"
|
||||
)
|
||||
if no_cache in argv:
|
||||
argv.remove(no_cache)
|
||||
|
||||
module.replace_flag = replace_and_override
|
||||
module.parse_args = lambda: args
|
||||
module.main()
|
||||
|
||||
manifest_path = args.output_root / "manifest.json"
|
||||
manifest = json.loads(manifest_path.read_text())
|
||||
manifest.update(
|
||||
{
|
||||
"schema": "frontier-attn-structured-replay-v1",
|
||||
"frontier_base_commit": BASE_COMMIT,
|
||||
"frontier_experiment_commit": EXPERIMENT_COMMIT,
|
||||
"frontier_patch": str(PATCH.resolve()),
|
||||
"frontier_patch_sha256": module.sha256(PATCH),
|
||||
"attention_profile_override": str(profile),
|
||||
"attention_profile_sha256": module.sha256(profile),
|
||||
"model_cache_enabled": True,
|
||||
}
|
||||
)
|
||||
manifest_path.write_text(json.dumps(manifest, indent=2))
|
||||
print(f"structured replay done: {args.output_root}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user