xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-11 22:44:32 +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
the model serving engine."""
enable_request_id_headers: bool = False
"""If specified, API server will add X-Request-Id header to responses.
Caution: this hurts performance at high QPS."""
"""If specified, API server will add X-Request-Id header to responses."""
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`
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
"""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.