vllm-ascend
Run and adapt large AI models on Huawei Ascend NPU hardware
All Skills in This Repository (4)
Pure Emerald Level Indicators
vllm-projectmain2main
Analyze vLLM commit differences and generate prioritized adaptation reports for vLLM Ascend.
vllm-projectvLLM Ascend Release Note Writer
Generate vLLM Ascend release notes by analyzing commits between tags.
vllm-projectvllm-ascend-model-adapter
Adapts ML models for vLLM-Ascend NPUs with deterministic validation and signing.
vllm-projectvllm-ascend-release
Automates the end-to-end release management workflow for vLLM Ascend on GitHub.
Frequently Asked Questions
FAQPage SchemaHow to install vllm-ascend?▼
Run `npx skills add vllm-project/vllm-ascend --all -g -y` in your terminal to install all skills in this suite globally.
What does vLLM Ascend do?▼
It is a hardware plugin that lets the vLLM inference engine run large language and multimodal models on Huawei Ascend NPU chips instead of GPUs.
How to run a new model on Ascend NPU?▼
The model adapter skill guides your AI agent through registering the architecture, mapping weights, and validating inference with real checkpoints on Ascend hardware.
Can AI automate the vLLM Ascend release process?▼
Yes. The release skill creates checklist issues, triages bugs, drafts release notes, and prepares announcements while keeping human approval at critical steps.
Does vllm-ascend work with Claude Code and other AI agents?▼
Yes. All skills follow the universal SKILL.md standard and run in Claude Code, OpenClaw, Cursor, and other compatible agents.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core