biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Add vllm bench sweep to CLI (#27639)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-10-29 20:59:48 +08:00
committed by GitHub
parent 9a0d2f0d92
commit ecca3fee76
19 changed files with 340 additions and 168 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
docs/mkdocs/hooks/generate_argparse.py
View File

@@ -56,15 +56,20 @@ def auto_mock(module, attr, max_mocks=50):
)
latency = auto_mock("vllm.benchmarks", "latency")
serve = auto_mock("vllm.benchmarks", "serve")
throughput = auto_mock("vllm.benchmarks", "throughput")
bench_latency = auto_mock("vllm.benchmarks", "latency")
bench_serve = auto_mock("vllm.benchmarks", "serve")
bench_sweep_plot = auto_mock("vllm.benchmarks.sweep.plot", "SweepPlotArgs")
bench_sweep_serve = auto_mock("vllm.benchmarks.sweep.serve", "SweepServeArgs")
bench_sweep_serve_sla = auto_mock(
"vllm.benchmarks.sweep.serve_sla", "SweepServeSLAArgs"
)
bench_throughput = auto_mock("vllm.benchmarks", "throughput")
AsyncEngineArgs = auto_mock("vllm.engine.arg_utils", "AsyncEngineArgs")
EngineArgs = auto_mock("vllm.engine.arg_utils", "EngineArgs")
ChatCommand = auto_mock("vllm.entrypoints.cli.openai", "ChatCommand")
CompleteCommand = auto_mock("vllm.entrypoints.cli.openai", "CompleteCommand")
cli_args = auto_mock("vllm.entrypoints.openai", "cli_args")
run_batch = auto_mock("vllm.entrypoints.openai", "run_batch")
openai_cli_args = auto_mock("vllm.entrypoints.openai", "cli_args")
openai_run_batch = auto_mock("vllm.entrypoints.openai", "run_batch")
FlexibleArgumentParser = auto_mock(
"vllm.utils.argparse_utils", "FlexibleArgumentParser"
)
@@ -114,6 +119,9 @@ class MarkdownFormatter(HelpFormatter):
self._markdown_output.append(f"{action.help}\n\n")
if (default := action.default) != SUPPRESS:
# Make empty string defaults visible
if default == "":
default = '""'
self._markdown_output.append(f"Default: `{default}`\n\n")
def format_help(self):
@@ -150,17 +158,23 @@ def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
# Create parsers to document
parsers = {
# Engine args
"engine_args": create_parser(EngineArgs.add_cli_args),
"async_engine_args": create_parser(
AsyncEngineArgs.add_cli_args, async_args_only=True
),
"serve": create_parser(cli_args.make_arg_parser),
# CLI
"serve": create_parser(openai_cli_args.make_arg_parser),
"chat": create_parser(ChatCommand.add_cli_args),
"complete": create_parser(CompleteCommand.add_cli_args),
"bench_latency": create_parser(latency.add_cli_args),
"bench_throughput": create_parser(throughput.add_cli_args),
"bench_serve": create_parser(serve.add_cli_args),
"run-batch": create_parser(run_batch.make_arg_parser),
"run-batch": create_parser(openai_run_batch.make_arg_parser),
# Benchmark CLI
"bench_latency": create_parser(bench_latency.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_serve": create_parser(bench_sweep_serve.add_cli_args),
"bench_sweep_serve_sla": create_parser(bench_sweep_serve_sla.add_cli_args),
"bench_throughput": create_parser(bench_throughput.add_cli_args),
}
# Generate documentation for each parser