testing-fwd-bwd-kernels
testing-fwd-bwd-kernels is a Model training & evaluation skill for AI agents, published by sablin39 in the tilelang-cuda-skills repository on GitHub. Skillspace rates testing-fwd-bwd-kernels D (66/100) and it passed the safety scan; the rating is based on static analysis only.
How to write and test TileLang kernels that need both forward and backward passes. Use this skill whenever the user is implementing custom operators with gradients, writing attention forward+backward, linear attention fwd+bwd, any op used inside torch.autograd.Function, or debugging gradient mismatches. Also trigger when the user mentions backward pass, gradients, dQ/dK/dV, autograd, ctx.save_for_backward, atomic_add for gradient accumulation, or gradient testing in TileLang context. Use even for questions like "how do I test my TileLang backward kernel" or "my gradients don't match the reference".
- Grade
- D
- Quality
- 66 / 100
- Safety
- Passed
- GitHub stars
- 131
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
- 84 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 1 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.