From bba01338ca866192318b23afbce5bd2ece8f13cf Mon Sep 17 00:00:00 2001
From: inkcherry <mingzhi.liu@amd.com>
Date: Wed, 17 Dec 2025 08:36:11 +0000
Subject: [PATCH] remove merge

Signed-off-by: inkcherry <mingzhi.liu@amd.com>
---
 vllm/entrypoints/openai/serving_chat.py       | 1 -
 vllm/entrypoints/openai/serving_completion.py | 1 -
 vllm/entrypoints/openai/serving_engine.py     | 3 ---
 3 files changed, 5 deletions(-)

diff --git a/vllm/entrypoints/openai/serving_chat.py b/vllm/entrypoints/openai/serving_chat.py
index 37fc5e4a9a9d7..9a7051e0920af 100644
--- a/vllm/entrypoints/openai/serving_chat.py
+++ b/vllm/entrypoints/openai/serving_chat.py
@@ -335,7 +335,6 @@ class OpenAIServingChat(OpenAIServing):
                         lora_request=lora_request,
                         trace_headers=trace_headers,
                         priority=request.priority,
-                        data_parallel_rank=data_parallel_rank,
                     )
 
                     generator = self.engine_client.generate(
diff --git a/vllm/entrypoints/openai/serving_completion.py b/vllm/entrypoints/openai/serving_completion.py
index 6cf000c3e79c1..9681aa8c71e6d 100644
--- a/vllm/entrypoints/openai/serving_completion.py
+++ b/vllm/entrypoints/openai/serving_completion.py
@@ -226,7 +226,6 @@ class OpenAIServingCompletion(OpenAIServing):
                         lora_request=lora_request,
                         trace_headers=trace_headers,
                         priority=request.priority,
-                        data_parallel_rank=data_parallel_rank,
                     )
 
                     generator = self.engine_client.generate(
diff --git a/vllm/entrypoints/openai/serving_engine.py b/vllm/entrypoints/openai/serving_engine.py
index 624b936814b69..d9feee917ff4e 100644
--- a/vllm/entrypoints/openai/serving_engine.py
+++ b/vllm/entrypoints/openai/serving_engine.py
@@ -1207,7 +1207,6 @@ class OpenAIServing:
         lora_request: LoRARequest | None,
         trace_headers: Mapping[str, str] | None,
         priority: int,
-        data_parallel_rank: int | None,
     ) -> tuple[EngineCoreRequest, dict[str, Any]]:
         """Use the Processor to process inputs for AsyncLLM."""
         tokenization_kwargs: dict[str, Any] = {}
@@ -1223,7 +1222,6 @@ class OpenAIServing:
             tokenization_kwargs=tokenization_kwargs,
             trace_headers=trace_headers,
             priority=priority,
-            data_parallel_rank=data_parallel_rank,
         )
         return engine_request, tokenization_kwargs
 
@@ -1258,7 +1256,6 @@ class OpenAIServing:
                 lora_request=lora_request,
                 trace_headers=trace_headers,
                 priority=priority,
-                data_parallel_rank=None,
             )
 
             generator = self.engine_client.generate(