[Benchmark] Add vllm bench forward: exact-shape forward timing (#61339)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Woosuk Kwon
2026-10-14 10:52:26 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 2c74fd1873
commit 9d3dfa2886
14 changed files with 1320 additions and 1 deletions
+1
View File
@@ -38,6 +38,7 @@ def maybe_exec_rust_bench() -> None:
def _import_bench_subcommand_modules() -> None:
# Imported lazily so `BenchmarkSubcommandBase` subclasses register only
# when `vllm bench` is actually invoked.
import vllm.entrypoints.cli.benchmark.forward # noqa: F401
import vllm.entrypoints.cli.benchmark.latency # noqa: F401
import vllm.entrypoints.cli.benchmark.mm_processor # noqa: F401
import vllm.entrypoints.cli.benchmark.serve # noqa: F401