[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
+22
View File
@@ -0,0 +1,22 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import argparse
from vllm.benchmarks.forward.main import add_cli_args, main
from vllm.entrypoints.cli.benchmark.base import BenchmarkSubcommandBase
from vllm.utils.argparse_utils import FlexibleArgumentParser
class BenchmarkForwardSubcommand(BenchmarkSubcommandBase):
"""The `forward` subcommand for `vllm bench`."""
name = "forward"
help = "Benchmark the model forward of exact batches as CUDA graphs."
@classmethod
def add_cli_args(cls, parser: FlexibleArgumentParser) -> None:
add_cli_args(parser)
@staticmethod
def cmd(args: argparse.Namespace) -> None:
main(args)