triton-cuda-attention
triton-cuda-attention is a Model training & evaluation skill for AI agents, published by mindspore-ai in the akg repository on GitHub. Skillspace rates triton-cuda-attention C (70/100) and it passed the safety scan; the rating is based on static analysis only.
Attention 算子的 Triton-CUDA 实现指南。包含经过验证的 Flash Attention 完整示例、各变体（Causal/GQA/MQA/RoPE）的差异改法、在线 Softmax 算法和常见错误
- Grade
- C
- Quality
- 70 / 100
- Safety
- Passed
- GitHub stars
- 255
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 92 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Apache-2.0
- Adoption
- Adopted by 2 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.