xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-14 06:41:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove merge

Browse Source 
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
This commit is contained in:
inkcherry 2025-12-17 08:36:11 +00:00
parent f98cde1997
commit bba01338ca
3 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -335,7 +335,6 @@ class OpenAIServingChat(OpenAIServing):
lora_request=lora_request, lora_request=lora_request,
trace_headers=trace_headers, trace_headers=trace_headers,
priority=request.priority, priority=request.priority,
data_parallel_rank=data_parallel_rank,
) )
generator = self.engine_client.generate( generator = self.engine_client.generate(

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

@ -226,7 +226,6 @@ class OpenAIServingCompletion(OpenAIServing):
lora_request=lora_request, lora_request=lora_request,
trace_headers=trace_headers, trace_headers=trace_headers,
priority=request.priority, priority=request.priority,
data_parallel_rank=data_parallel_rank,
) )
generator = self.engine_client.generate( generator = self.engine_client.generate(

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

@ -1207,7 +1207,6 @@ class OpenAIServing:
lora_request: LoRARequest | None, lora_request: LoRARequest | None,
trace_headers: Mapping[str, str] | None, trace_headers: Mapping[str, str] | None,
priority: int, priority: int,
data_parallel_rank: int | None,
) -> tuple[EngineCoreRequest, dict[str, Any]]: ) -> tuple[EngineCoreRequest, dict[str, Any]]:
"""Use the Processor to process inputs for AsyncLLM.""" """Use the Processor to process inputs for AsyncLLM."""
tokenization_kwargs: dict[str, Any] = {} tokenization_kwargs: dict[str, Any] = {}
@ -1223,7 +1222,6 @@ class OpenAIServing:
tokenization_kwargs=tokenization_kwargs, tokenization_kwargs=tokenization_kwargs,
trace_headers=trace_headers, trace_headers=trace_headers,
priority=priority, priority=priority,
data_parallel_rank=data_parallel_rank,
) )
return engine_request, tokenization_kwargs return engine_request, tokenization_kwargs
@ -1258,7 +1256,6 @@ class OpenAIServing:
lora_request=lora_request, lora_request=lora_request,
trace_headers=trace_headers, trace_headers=trace_headers,
priority=priority, priority=priority,
data_parallel_rank=None,
) )
generator = self.engine_client.generate( generator = self.engine_client.generate(