Stanford CRFM company blog
Surprisingly fast AI-generated kernels we didn't mean to publish yet
We have some very fast AI-generated kernels in pure CUDA-C without using libraries and DSLs such as CUTLASS and Triton. They are performing close to or in some cases even beating the standard expert-optimized production kernels shipped in PyTorch. Some of our highlighted results:
- Points
- 417
- HN comments
- 217
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSystems & Performance2025
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| May 30, 2025 | Surprisingly fast AI-generated kernels we didn't mean to publish yet by mfiguiere | 417 | 217 |
