change serving_completion back

LunrEclipse · LunrEclipse · commit 097479dd5867 · 2024-10-07T22:22:30.000Z
diff --git a/vllm/entrypoints/openai/serving_completion.py b/vllm/entrypoints/openai/serving_completion.py
@@ -158,7 +158,7 @@ async def create_completion(
                     "AsyncLLMEngine and MQLLMEngineClient."
                     generator = self.engine_client.beam_search(
                         prompt_inputs["prompt_token_ids"],
-                        request_id,
+                        request_id_item,
                         sampling_params,
                     )
                 else:

Original file line number	Diff line number	Diff line change
`@@ -158,7 +158,7 @@ async def create_completion(`
`158`	`158`	`"AsyncLLMEngine and MQLLMEngineClient."`
`159`	`159`	`generator = self.engine_client.beam_search(`
`160`	`160`	`prompt_inputs["prompt_token_ids"],`
`161`		`- request_id,`
	`161`	`+ request_id_item,`
`162`	`162`	`sampling_params,`
`163`	`163`	`)`
`164`	`164`	`else:`