From 044e486480cd4ce62bae15529403469a6c231dd0 Mon Sep 17 00:00:00 2001 From: Xiangyu Tian <109123695+xiangyuT@users.noreply.github.com> Date: Fri, 9 Aug 2024 10:33:52 +0800 Subject: [PATCH] Fix vLLM CPU /chat endpoint (#11748) --- .../llm/src/ipex_llm/vllm/cpu/entrypoints/openai/api_server.py | 1 - 1 file changed, 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 index 5065f1c1..c9cae077 100644 --- 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())