[Doc] Sync CLI guide with actual help modes and launch subcommand (#40326)

Signed-off-by: Rui Wang <raygorous@gmail.com>
Co-authored-by: Rui Wang <raygorous@gmail.com>
This commit is contained in:
Ray Wang
2026-05-20 02:32:03 -07:00
committed by GitHub
co-authored by Rui Wang
parent cb600d1cdb
commit 87e31455b0
4 changed files with 46 additions and 8 deletions
+2
View File
@@ -147,6 +147,7 @@ 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")
RenderSubcommand = auto_mock("vllm.entrypoints.cli.launch", "RenderSubcommand")
openai_cli_args = auto_mock("vllm.entrypoints.openai", "cli_args")
openai_run_batch = auto_mock("vllm.entrypoints.openai", "run_batch")
@@ -260,6 +261,7 @@ def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
"serve": create_parser(openai_cli_args.make_arg_parser),
"chat": create_parser(ChatCommand.add_cli_args),
"complete": create_parser(CompleteCommand.add_cli_args),
"launch_render": create_parser(RenderSubcommand.add_cli_args),
"run-batch": create_parser(openai_run_batch.make_arg_parser),
# Benchmark CLI
"bench_latency": create_parser(bench_latency.add_cli_args),