support chat completion with multi model

Signed-off-by: Chendi.Xue <[email protected]>
HabanaAI · Jan 10, 2025 · 1ea9d6c · 1ea9d6c
1 parent 844c146
commit 1ea9d6c
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/vllm/entrypoints/openai/serving_chat.py b/vllm/entrypoints/openai/serving_chat.py
@@ -221,6 +221,7 @@ async def create_chat_completion(
                         engine_prompt,
                         sampling_params,
                         request_id,
+                        model = request.model,
                         lora_request=lora_request,
                         trace_headers=trace_headers,
                         prompt_adapter_request=prompt_adapter_request,