[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
+18
View File
@@ -55,6 +55,8 @@ class ForwardBench:
iters: int,
samples: int,
state_views: list[torch.Tensor],
name: str,
profile_prefix: str | None = None,
):
self.runner = runner
self.batch = batch
@@ -62,6 +64,8 @@ class ForwardBench:
self.iters = iters
self.samples = samples
self.state_views = state_views
self.name = name
self.profile_prefix = profile_prefix
self.phase = "warmup"
self.result: dict[str, Any] = {}
@@ -193,6 +197,20 @@ class ForwardBench:
),
)
self.result["latency_us"] = self._time(graph)
from vllm.benchmarks.forward.profile import profile_graph
# Each replay restores the state views, then (multi-rank) rendezvouses,
# before the timed forward.
skip = len(self.state_views) + (world.world_size > 1)
summary = profile_graph(graph, self.name, self.profile_prefix, skip)
if summary is not None:
self.result["profile"] = {
"summary": f"{self.profile_prefix}.kernels.json",
"span_us": summary["span_us"],
"busy_us": summary["busy_us"],
"activities": summary["activities"],
"top_kernels": summary["kernels"][:10],
}
del graph
return output