[Misc][V0 Deprecation] Add __main__ guard to all offline examples (#1837)

### What this PR does / why we need it?
Add `__main__` guard to all offline examples.

- vLLM version: v0.9.2
- vLLM main:
76b494444f

---------

Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
Shanshan Shen
2025-07-17 14:13:30 +08:00
committed by GitHub
parent 19e37cd379
commit aeb5aa8b88
15 changed files with 157 additions and 87 deletions

View File

@@ -17,28 +17,37 @@
# Adapted from vllm-project/vllm/examples/offline_inference/basic.py
#
import os
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
# 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,
)
def main():
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# 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}")
# 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()