Add Multimodal Processor Benchmark (#29105)

Signed-off-by: Reagan Lee <reaganjlee@gmail.com>
Signed-off-by: Reagan <reaganjlee@gmail.com>
This commit is contained in:
Reagan Lee
2026-01-01 19:26:53 -08:00
committed by GitHub
parent adcf682fc7
commit 1f5b7c41c3
13 changed files with 1035 additions and 222 deletions

View File

@@ -92,6 +92,7 @@ def auto_mock(module_name: str, attr: str, max_mocks: int = 100):
bench_latency = auto_mock("vllm.benchmarks", "latency")
bench_mm_processor = auto_mock("vllm.benchmarks", "mm_processor")
bench_serve = auto_mock("vllm.benchmarks", "serve")
bench_sweep_plot = auto_mock("vllm.benchmarks.sweep.plot", "SweepPlotArgs")
bench_sweep_plot_pareto = auto_mock(
@@ -222,6 +223,7 @@ def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
"run-batch": create_parser(openai_run_batch.make_arg_parser),
# Benchmark CLI
"bench_latency": create_parser(bench_latency.add_cli_args),
"bench_mm_processor": create_parser(bench_mm_processor.add_cli_args),
"bench_serve": create_parser(bench_serve.add_cli_args),
"bench_sweep_plot": create_parser(bench_sweep_plot.add_cli_args),
"bench_sweep_plot_pareto": create_parser(bench_sweep_plot_pareto.add_cli_args),