xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 09:24:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] - Add Trace Headers to Beam Search Path (#29100)

Browse Source 
Signed-off-by: dsuhinin <suhinin.dmitriy@gmail.com>
This commit is contained in:
Software Developer 2025-11-20 21:00:33 +01:00 committed by GitHub
parent 114b0e2500
commit 4d01b64284
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/entrypoints/openai/serving_chat.py
View File

@ -319,6 +319,7 @@ class OpenAIServingChat(OpenAIServing):
request_id=request_id,
params=sampling_params,
lora_request=lora_request,
trace_headers=trace_headers,
)
else:
engine_request, tokenization_kwargs = await self._process_inputs(

1
vllm/entrypoints/openai/serving_completion.py
View File

@ -216,6 +216,7 @@ class OpenAIServingCompletion(OpenAIServing):
request_id=request_id,
params=sampling_params,
lora_request=lora_request,
trace_headers=trace_headers,
)
else:
engine_request, tokenization_kwargs = await self._process_inputs(

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

@ -343,6 +343,7 @@ class OpenAIServing:
request_id: str,
params: BeamSearchParams,
lora_request: LoRARequest | None = None,
trace_headers: Mapping[str, str] | None = None,
) -> AsyncGenerator[RequestOutput, None]:
beam_width = params.beam_width
max_tokens = params.max_tokens
@ -437,6 +438,7 @@ class OpenAIServing:
beam_search_params,
request_id_item,
lora_request=lora_req,
trace_headers=trace_headers,
)
)
)