Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
PowerRetention: a drop-in replacement for FlashAttention in LLMs (github.com/m-a-n-i-f-e-s-t)
2 points by dvrp 84 days ago | past | 2 comments
Power Attention: Efficient CUDA Kernels for Symmetric Power Transformers (github.com/m-a-n-i-f-e-s-t)
6 points by txus 10 months ago | past | 2 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: