[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:
co-authored by
Claude Opus 5.5
parent
2c74fd1873
commit
9d3dfa2886
@@ -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)
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user