[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

@@ -19,35 +19,40 @@
import os
os.environ["VLLM_USE_MODELSCOPE"] = "True"
import torch
from vllm import LLM
os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery:{query}'
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
def main():
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, 'What is the capital of China?'),
get_detailed_instruct(task, 'Explain gravity')
]
# No need to add instruction for retrieval documents
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
]
input_texts = queries + documents
queries = [
get_detailed_instruct(task, 'What is the capital of China?'),
get_detailed_instruct(task, 'Explain gravity')
]
# No need to add instruction for retrieval documents
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
]
input_texts = queries + documents
model = LLM(model="Qwen/Qwen3-Embedding-0.6B", task="embed")
model = LLM(model="Qwen/Qwen3-Embedding-0.6B", task="embed")
outputs = model.embed(input_texts)
embeddings = torch.tensor([o.outputs.embedding for o in outputs])
# Calculate the similarity scores between the first two queries and the last two documents
scores = (embeddings[:2] @ embeddings[2:].T)
print(scores.tolist())
# [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]
outputs = model.embed(input_texts)
embeddings = torch.tensor([o.outputs.embedding for o in outputs])
# Calculate the similarity scores between the first two queries and the last two documents
scores = (embeddings[:2] @ embeddings[2:].T)
print(scores.tolist())
# [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]
if __name__ == "__main__":
main()