xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-25 23:44:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

Replace --expand-tools-even-if-tool-choice-none with --exclude-tools-when-tool-choice-none for v0.10.0 (#20544)

Browse Source 
Signed-off-by: okada <kokuzen@gmail.com>
Signed-off-by: okada shintarou <okada@preferred.jp>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Shintarou Okada 2025-07-24 18:56:36 +09:00 committed by GitHub
parent 85bda9e7d0
commit 6eca337ce0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docs/features/tool_calling.md
View File

@ -103,7 +103,8 @@ When tool_choice='required' is set, the model is guaranteed to generate one or m
vLLM supports the `tool_choice='none'` option in the chat completion API. When this option is set, the model will not generate any tool calls and will respond with regular text content only, even if tools are defined in the request.
However, when `tool_choice='none'` is specified, vLLM includes tool definitions from the prompt.
!!! note
When tools are specified in the request, vLLM includes tool definitions in the prompt by default, regardless of the `tool_choice` setting. To exclude tool definitions when `tool_choice='none'`, use the `--exclude-tools-when-tool-choice-none` option.
## Automatic Function Calling

2
vllm/entrypoints/openai/api_server.py
View File

@ -1646,6 +1646,8 @@ async def init_app_state(
chat_template_content_format=args.chat_template_content_format,
return_tokens_as_token_ids=args.return_tokens_as_token_ids,
enable_auto_tools=args.enable_auto_tool_choice,
exclude_tools_when_tool_choice_none=args.
exclude_tools_when_tool_choice_none,
tool_parser=args.tool_call_parser,
reasoning_parser=args.reasoning_parser,
enable_prompt_tokens_details=args.enable_prompt_tokens_details,

3
vllm/entrypoints/openai/cli_args.py
View File

@ -133,6 +133,9 @@ schema. Example: `[{"type": "text", "text": "Hello world!"}]`"""
"""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
"""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."""
tool_call_parser: Optional[str] = None

7
vllm/entrypoints/openai/serving_chat.py
View File

@ -63,6 +63,7 @@ class OpenAIServingChat(OpenAIServing):
return_tokens_as_token_ids: bool = False,
reasoning_parser: str = "",
enable_auto_tools: bool = False,
exclude_tools_when_tool_choice_none: bool = False,
tool_parser: Optional[str] = None,
enable_prompt_tokens_details: bool = False,
enable_force_include_usage: bool = False,
@ -111,6 +112,8 @@ class OpenAIServingChat(OpenAIServing):
raise TypeError("Error: --enable-auto-tool-choice requires "
f"tool_parser:'{tool_parser}' which has not "
"been registered") from e
self.exclude_tools_when_tool_choice_none = (
exclude_tools_when_tool_choice_none)
self.enable_prompt_tokens_details = enable_prompt_tokens_details
self.enable_force_include_usage = enable_force_include_usage
@ -174,7 +177,9 @@ class OpenAIServingChat(OpenAIServing):
"--enable-auto-tool-choice and --tool-call-parser to be set"
)
if request.tools is None:
if (request.tools is None
or (request.tool_choice == "none"
and self.exclude_tools_when_tool_choice_none)):
tool_dicts = None
else:
tool_dicts = [tool.model_dump() for tool in request.tools]