EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Lint]Style: Convert example to ruff format (#5863)

Browse Source 
### What this PR does / why we need it?
This PR fixes linting issues in the `example/` to align with the
project's Ruff configuration.

- vLLM version: v0.13.0
- vLLM main:
bde38c11df

Signed-off-by: root <root@LAPTOP-VQKDDVMG.localdomain>
Co-authored-by: root <root@LAPTOP-VQKDDVMG.localdomain>
This commit is contained in:
SILONG ZENG
2026-01-13 20:46:50 +08:00
committed by GitHub
parent f7b904641e
commit 78d5ce3e01
23 changed files with 678 additions and 1037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/offline_embed.py
View File

@@ -25,22 +25,24 @@ 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}'
return f"Instruct: {task_description}\nQuery:{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'
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')
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."
"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
@@ -49,7 +51,7 @@ def main():
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)
scores = embeddings[:2] @ embeddings[2:].T
print(scores.tolist())
# [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]