[Doc] add chat_template_kwagrs and update params docs (#3103)

* add chat_template_kwagrs and update params docs

* add chat_template_kwagrs and update params docs

* update enable_thinking

* pre-commit

* update test case

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
LiqinruiG
2025-07-31 19:44:06 +08:00
committed by GitHub
parent 22cab724e8
commit 25005fee30
11 changed files with 648 additions and 105 deletions

View File

@@ -129,11 +129,11 @@ class OpenAIServingChat:
if request.max_streaming_response_tokens is not None
else (request.metadata or {}).get("max_streaming_response_tokens", 1)
) # dierctly passed & passed in metadata
enable_thinking = (
request.enable_thinking
if request.enable_thinking is not None
else (request.metadata or {}).get("enable_thinking")
)
enable_thinking = request.chat_template_kwargs.get("enable_thinking") if request.chat_template_kwargs else None
if enable_thinking is None:
enable_thinking = request.metadata.get("enable_thinking") if request.metadata else None
include_stop_str_in_output = request.include_stop_str_in_output
stream_options = request.stream_options
@@ -330,11 +330,10 @@ class OpenAIServingChat:
"""
created_time = int(time.time())
final_res = None
enable_thinking = (
request.enable_thinking
if request.enable_thinking is not None
else (request.metadata or {}).get("enable_thinking")
)
enable_thinking = request.chat_template_kwargs.get("enable_thinking") if request.chat_template_kwargs else None
if enable_thinking is None:
enable_thinking = request.metadata.get("enable_thinking") if request.metadata else None
include_stop_str_in_output = request.include_stop_str_in_output
try: