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

[Frontend] Expose revision arg in OpenAI server (#8501)

Browse Source
This commit is contained in:
lewtun 2024-09-16 17:55:26 +02:00 committed by GitHub
parent a091e2da3e
commit 837c1968f9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/openai/api_server.py
View File

@ -69,8 +69,10 @@ _running_tasks: Set[asyncio.Task] = set()
def model_is_embedding(model_name: str, trust_remote_code: bool, def model_is_embedding(model_name: str, trust_remote_code: bool,
quantization: Optional[str]) -> bool: quantization: Optional[str],
revision: Optional[str]) -> bool:
return ModelConfig(model=model_name, return ModelConfig(model=model_name,
revision=revision,
tokenizer=model_name, tokenizer=model_name,
tokenizer_mode="auto", tokenizer_mode="auto",
trust_remote_code=trust_remote_code, trust_remote_code=trust_remote_code,
@ -130,7 +132,7 @@ async def build_async_engine_client_from_engine_args(
# If manually triggered or embedding model, use AsyncLLMEngine in process. # If manually triggered or embedding model, use AsyncLLMEngine in process.
# TODO: support embedding model via RPC. # TODO: support embedding model via RPC.
if (model_is_embedding(engine_args.model, engine_args.trust_remote_code, if (model_is_embedding(engine_args.model, engine_args.trust_remote_code,
engine_args.quantization) engine_args.quantization, engine_args.revision)
or disable_frontend_multiprocessing): or disable_frontend_multiprocessing):
engine_client = AsyncLLMEngine.from_engine_args( engine_client = AsyncLLMEngine.from_engine_args(
engine_args, usage_context=UsageContext.OPENAI_API_SERVER) engine_args, usage_context=UsageContext.OPENAI_API_SERVER)