xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-04 07:02:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[doc] update vllm serve cli args documentation (#24329)

Browse Source 
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
This commit is contained in:
cjackal 2025-09-09 12:07:58 +09:00 committed by GitHub
parent 22a0070530
commit 13b89bd823
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
vllm/entrypoints/openai/cli_args.py
View File

@ -134,14 +134,13 @@ schema. Example: `[{"type": "text", "text": "Hello world!"}]`"""
"""If specified, will run the OpenAI frontend server in the same process as """If specified, will run the OpenAI frontend server in the same process as
the model serving engine.""" the model serving engine."""
enable_request_id_headers: bool = False enable_request_id_headers: bool = False
"""If specified, API server will add X-Request-Id header to responses. """If specified, API server will add X-Request-Id header to responses."""
Caution: this hurts performance at high QPS."""
enable_auto_tool_choice: bool = False enable_auto_tool_choice: bool = False
"""If specified, exclude tool definitions in prompts when
tool_choice='none'."""
exclude_tools_when_tool_choice_none: bool = False
"""Enable auto tool choice for supported models. Use `--tool-call-parser` """Enable auto tool choice for supported models. Use `--tool-call-parser`
to specify which parser to use.""" to specify which parser to use."""
exclude_tools_when_tool_choice_none: bool = False
"""If specified, exclude tool definitions in prompts when
tool_choice='none'."""
tool_call_parser: Optional[str] = None tool_call_parser: Optional[str] = None
"""Select the tool call parser depending on the model that you're using. """Select the tool call parser depending on the model that you're using.
This is used to parse the model-generated tool call into OpenAI API format. This is used to parse the model-generated tool call into OpenAI API format.