biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc][LoRA] Ensure Lora Adapter requests return adapter name (#11094)

Browse Source 
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jiaxin Shan
2024-12-12 01:25:16 -08:00
committed by GitHub
parent 62de37a38e
commit 85362f028c
4 changed files with 33 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
vllm/entrypoints/openai/serving_chat.py
View File

@@ -123,6 +123,8 @@ class OpenAIServingChat(OpenAIServing):
prompt_adapter_request,
) = self._maybe_get_adapters(request)
model_name = self._get_model_name(lora_request)
tokenizer = await self.engine_client.get_tokenizer(lora_request)
tool_parser = self.tool_parser
@@ -238,13 +240,13 @@ class OpenAIServingChat(OpenAIServing):
# Streaming response
if request.stream:
return self.chat_completion_stream_generator(
request, result_generator, request_id, conversation, tokenizer,
request_metadata)
request, result_generator, request_id, model_name,
conversation, tokenizer, request_metadata)
try:
return await self.chat_completion_full_generator(
request, result_generator, request_id, conversation, tokenizer,
request_metadata)
request, result_generator, request_id, model_name,
conversation, tokenizer, request_metadata)
except ValueError as e:
# TODO: Use a vllm-specific Validation Error
return self.create_error_response(str(e))
@@ -259,11 +261,11 @@ class OpenAIServingChat(OpenAIServing):
request: ChatCompletionRequest,
result_generator: AsyncIterator[RequestOutput],
request_id: str,
model_name: str,
conversation: List[ConversationMessage],
tokenizer: AnyTokenizer,
request_metadata: RequestResponseMetadata,
) -> AsyncGenerator[str, None]:
model_name = self.base_model_paths[0].name
created_time = int(time.time())
chunk_object_type: Final = "chat.completion.chunk"
first_iteration = True
@@ -604,12 +606,12 @@ class OpenAIServingChat(OpenAIServing):
request: ChatCompletionRequest,
result_generator: AsyncIterator[RequestOutput],
request_id: str,
model_name: str,
conversation: List[ConversationMessage],
tokenizer: AnyTokenizer,
request_metadata: RequestResponseMetadata,
) -> Union[ErrorResponse, ChatCompletionResponse]:
model_name = self.base_model_paths[0].name
created_time = int(time.time())
final_res: Optional[RequestOutput] = None