From a66ef39bb6824f6406e3296c06d35c17ec173109 Mon Sep 17 00:00:00 2001
From: Shanshan Shen <467638484@qq.com>
Date: Mon, 21 Jul 2025 12:01:45 +0800
Subject: [PATCH] [Misc][V0 Deprecation] Remove Redundant Offline Distributed
 Inference Example (#1899)

### What this PR does / why we need it?
The file `offline_distributed_inference_npu.py` is the same as
`offline_inference_npu_tp2.py`, thus we delete one of them.

This PR is a part of
https://github.com/vllm-project/vllm-ascend/issues/1620.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.9.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/8188196a1c8af26134d8e366ebe564c18fb95379

Signed-off-by: shen-shanshan <467638484@qq.com>
---
 examples/offline_distributed_inference_npu.py | 53 -------------------
 1 file changed, 53 deletions(-)
 delete mode 100644 examples/offline_distributed_inference_npu.py

diff --git a/examples/offline_distributed_inference_npu.py b/examples/offline_distributed_inference_npu.py
deleted file mode 100644
index 4e2e7ed..0000000
--- a/examples/offline_distributed_inference_npu.py
+++ /dev/null
@@ -1,53 +0,0 @@
-#
-# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
-# Copyright 2023 The vLLM team.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-# This file is a part of the vllm-ascend project.
-# Adapted from vllm-project/vllm/examples/offline_inference/basic.py
-#
-
-import os
-from vllm import LLM, SamplingParams
-
-os.environ["VLLM_USE_MODELSCOPE"] = "True"
-os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
-
-def main():
-    prompts = [
-        "Hello, my name is",
-        "The president of the United States is",
-        "The capital of France is",
-        "The future of AI is",
-    ]
-
-    # Create a sampling params object.
-    sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
-    # Create an LLM.
-    llm = LLM(
-        model="Qwen/Qwen2.5-0.5B-Instruct",
-        tensor_parallel_size=2,
-        distributed_executor_backend="mp",
-        trust_remote_code=True,
-    )
-
-    # Generate texts from the prompts.
-    outputs = llm.generate(prompts, sampling_params)
-    for output in outputs:
-        prompt = output.prompt
-        generated_text = output.outputs[0].text
-        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
-
-
-if __name__ == "__main__":
-    main()