[Benchmark] Add per-case kernel profiles to vllm bench forward (#61692)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
This commit is contained in:
Woosuk Kwon
2026-10-17 08:27:11 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 vllm-agent
parent c61a1e73c6
commit c0b6f74bee
6 changed files with 356 additions and 1 deletions
+37
View File
@@ -3,6 +3,7 @@
import json
import subprocess
from dataclasses import replace
from pathlib import Path
from types import SimpleNamespace
import numpy as np
@@ -10,6 +11,7 @@ import pytest
from vllm.benchmarks.forward.batch import build_batch
from vllm.benchmarks.forward.main import run_case
from vllm.benchmarks.forward.profile import summarize
from vllm.benchmarks.forward.shapes import jitter_kv_lens, parse_case
from vllm.platforms import current_platform
@@ -97,6 +99,35 @@ def test_bench_forward_rejects_oversized_verify(capacity):
run_case(runner, case, SimpleNamespace())
def test_profile_summary():
"""Each replay's leading restore/rendezvous activities are left out, and
kernels are grouped by name without template or function arguments."""
def act(name, ts, dur, cat="kernel"):
return {"cat": cat, "name": name, "ts": ts, "dur": dur}
replay = [
("Memcpy DtoD (Device -> Device)", "gpu_memcpy", 5),
("void ns::gemm<128>(Params)", "kernel", 10),
("void ns::gemm<64>(Params)", "kernel", 20),
("std::enable_if<(1>0), void>::type ns::norm<float>(float*)", "kernel", 4),
]
events = [{"cat": "cpu_op", "name": "x", "ts": 0, "dur": 1}]
for r in range(2):
for i, (name, cat, dur) in enumerate(replay):
events.append(act(name, 1000 * r + 100 * i, dur, cat))
summary = summarize(events, replays=2, skip=1)
assert summary["pre_forward_us"] == 5
assert summary["busy_us"] == 34
assert summary["span_us"] == 204
assert [(k["name"], k["us"], k["calls"]) for k in summary["kernels"]] == [
("ns::gemm", 30, 2),
("ns::norm", 4, 1),
]
with pytest.raises(ValueError, match="replays"):
summarize(events[:-1], replays=2, skip=1)
@pytest.mark.benchmark
# TODO(woosuk): Support ROCm and re-enable this test there.
@pytest.mark.skipif(
@@ -126,6 +157,8 @@ def test_bench_forward(tmp_path):
"2",
"--output-json",
str(output),
"--profile-dir",
str(tmp_path / "profile"),
]
result = subprocess.run(command, capture_output=True, text=True)
print(result.stdout)
@@ -139,3 +172,7 @@ def test_bench_forward(tmp_path):
assert len(rank0["batch_order"]) == len(row["requests"])
assert rank0["finite"] and rank0["graph_deterministic"]
assert row["median_us"] > 0
profile = rank0["profile"]
assert profile["top_kernels"] and profile["span_us"] > 0
summary = json.loads(Path(profile["summary"]).read_text())
assert Path(summary["trace"]).exists()