[Bugfix][Refactor] Unify model management in frontend (#11660)

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
This commit is contained in:
Joe Runde
2025-01-01 02:21:51 +00:00
committed by GitHub
parent 0c6f998554
commit 4db72e57f6
15 changed files with 365 additions and 307 deletions
+4 -5
View File
@@ -16,7 +16,8 @@ from vllm.entrypoints.openai.protocol import (EmbeddingChatRequest,
EmbeddingResponse,
EmbeddingResponseData,
ErrorResponse, UsageInfo)
from vllm.entrypoints.openai.serving_engine import BaseModelPath, OpenAIServing
from vllm.entrypoints.openai.serving_engine import OpenAIServing
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.logger import init_logger
from vllm.outputs import (EmbeddingOutput, EmbeddingRequestOutput,
PoolingRequestOutput)
@@ -46,7 +47,7 @@ class OpenAIServingEmbedding(OpenAIServing):
self,
engine_client: EngineClient,
model_config: ModelConfig,
base_model_paths: List[BaseModelPath],
models: OpenAIServingModels,
*,
request_logger: Optional[RequestLogger],
chat_template: Optional[str],
@@ -54,9 +55,7 @@ class OpenAIServingEmbedding(OpenAIServing):
) -> None:
super().__init__(engine_client=engine_client,
model_config=model_config,
base_model_paths=base_model_paths,
lora_modules=None,
prompt_adapters=None,
models=models,
request_logger=request_logger)
self.chat_template = chat_template