AI SummaryA skill for adapting and optimizing Hugging Face or custom LLM models to run efficiently on vLLM with Ascend NPU support, enabling developers to validate and deploy models with deterministic testing and single-commit delivery.
Description
Adapt and debug existing or new models for vLLM on Ascend NPU. Implement in /vllm-workspace/vllm and /vllm-workspace/vllm-ascend, validate via direct vllm serve from /workspace, and deliver one signed commit in the current repo.
Install
# Add to your project root as SKILL.md curl -o SKILL.md "https://raw.githubusercontent.com/vllm-project/vllm-ascend/main/.agents/skills/vllm-ascend-model-adapter/SKILL.md"
Quality Score
B
Good
80/100
Standard Compliance72
Documentation Quality65
Usefulness78
Maintenance Signal100
Community Signal100
Scored Today
Trust & Transparency
Open Source — Apache-2.0
Source code publicly auditable
Verified Open Source
Hosted on GitHub — publicly auditable
Actively Maintained
Last commit Yesterday
1.7k stars — Strong Community
853 forks
My Fox Den
Community Rating
Works With
Claude Code