Fix vLLM CPU /chat endpoint (#11748)

intel-analytics · Aug 9, 2024 · 044e486 · 044e486
1 parent 27b4b10
commit 044e486
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/python/llm/src/ipex_llm/vllm/cpu/entrypoints/openai/api_server.py b/python/llm/src/ipex_llm/vllm/cpu/entrypoints/openai/api_server.py
@@ -114,7 +114,6 @@ async def create_chat_completion(request: ChatCompletionRequest,
         return StreamingResponse(content=generator,
                                  media_type="text/event-stream")
     else:
-        invalidInputError(isinstance(generator, ChatCompletionResponse))
         return JSONResponse(content=generator.model_dump())