apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Pass through the chat_template_kwargs to the data processing module (#3421) (#3469)

Browse Source 
* fix chat_template_args

* fix args

* add offline

* add offline

* fix

* fix

* fix default enable_thinking value

* fix default enable_thinking value

* modify condition

* Revert "modify condition"

This reverts commit 26430bdeb1.

* fix unit test
This commit is contained in:
luukunn
2025-08-19 17:40:12 +08:00
committed by GitHub
parent 3ffbc98179
commit d07338f932
6 changed files with 50 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
fastdeploy/entrypoints/llm.py
View File

@@ -238,7 +238,7 @@ class LLM:
self,
prompts,
sampling_params,
chat_template_kwargs: Optional[dict[str, Any]] = None,
**kwargs,
):
"""
添加一个请求到 LLM Engine，并返回该请求的 ID。
@@ -279,10 +279,7 @@ class LLM:
current_sampling_params = sampling_params[i]
else:
current_sampling_params = sampling_params
enable_thinking = None
if chat_template_kwargs is not None:
enable_thinking = chat_template_kwargs.get("enable_thinking", None)
self.llm_engine.add_requests(tasks, current_sampling_params, enable_thinking=enable_thinking)
self.llm_engine.add_requests(tasks, current_sampling_params, **kwargs)
return req_ids
def _decode_token(self, token_id: int) -> str: