Gahow Wang
d5b276180d
Workload-conditioned operator profiling on patched vLLM 0.24.0 + Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64 raggedness, 8-45% token-efficiency loss vs rectangular controls); mechanism decomposition kills the padding narrative and finds the arrival-uniformization artifact (-12.9%); cross-version churn surface shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held. Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer sidecars and metrics are tracked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
69 lines
2.5 KiB
Python
69 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import subprocess
|
|
import sys
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
|
|
HERE = Path(__file__).resolve().parent
|
|
CLIENT = HERE / "opprof_phase5_client.py"
|
|
|
|
|
|
def write_jsonl(path: Path, rows: list[dict]) -> None:
|
|
path.write_text("".join(json.dumps(row) + "\n" for row in rows))
|
|
|
|
|
|
def run(command: list[str]) -> None:
|
|
completed = subprocess.run(command, text=True, capture_output=True)
|
|
if completed.returncode:
|
|
raise RuntimeError(f"command failed: {completed.stderr}")
|
|
|
|
|
|
def main() -> None:
|
|
with tempfile.TemporaryDirectory() as tmp_text:
|
|
tmp = Path(tmp_text)
|
|
manifest = tmp / "p3.jsonl"
|
|
source = tmp / "source.jsonl"
|
|
base = tmp / "base.jsonl"
|
|
a1 = tmp / "a1.jsonl"
|
|
rows = []
|
|
source_rows = []
|
|
lengths = [128, 8192, 256, 4096] * 8
|
|
for index, length in enumerate(lengths):
|
|
rows.append({
|
|
"request_id": f"P10-{index}", "pattern_id": "P10",
|
|
"input_tokens": length, "output_tokens": 8,
|
|
"arrival": "steady", "kind": "private-trace",
|
|
"source_index": index, "prompt": f"private-{index}",
|
|
})
|
|
source_rows.append({"timestamp": index * 0.1, "prompt": f"private-{index}"})
|
|
write_jsonl(manifest, rows)
|
|
write_jsonl(source, source_rows)
|
|
common = [
|
|
sys.executable, str(CLIENT), "transform", "--in", str(manifest),
|
|
"--take-first", "32", "--timestamp-source", str(source),
|
|
"--join-key", "source_index", "--timestamp-field", "timestamp",
|
|
"--arrival", "recorded-scaled", "--target-rate", "0.5",
|
|
]
|
|
run(common + ["--service-order", "original", "--out", str(base)])
|
|
run(common + [
|
|
"--service-order", "length-binned", "--reorder-block-size", "32",
|
|
"--analysis-cohort-size", "16", "--max-added-delay-seconds", "64",
|
|
"--out", str(a1),
|
|
])
|
|
base_summary = json.loads((base.with_suffix(".jsonl.summary.json")).read_text())
|
|
a1_summary = json.loads((a1.with_suffix(".jsonl.summary.json")).read_text())
|
|
assert base_summary["rows"] == a1_summary["rows"] == 32
|
|
assert base_summary["request_id_set_sha256"] == a1_summary["request_id_set_sha256"]
|
|
assert a1_summary["r16"] < base_summary["r16"]
|
|
assert a1_summary["max_added_delay_seconds"] <= 64
|
|
assert "private-" not in json.dumps(a1_summary)
|
|
print("phase5 tools: PASS")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|