Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
A Minimal KV Cache Manager for Paged Attention in ~100 Lines of Python (github.com/tspeterkim)
2 points by tspeterkim on July 1, 2024 | past
Show HN: Minimal Paged Attention (github.com/tspeterkim)
3 points by tspeterkim on June 28, 2024 | past
Insta-chat: simplest Instagram chat automation tool made with Google Sheets (github.com/tspeterkim)
1 point by thunderbong on June 1, 2024 | past
Show HN: DIY Instagram Automation for My Influencer Wife (github.com/tspeterkim)
3 points by tspeterkim on May 29, 2024 | past | 3 comments
Show HN: Mixed Precision Training from Scratch (github.com/tspeterkim)
1 point by tspeterkim on May 22, 2024 | past
Show HN: One Billion Rows in CUDA (github.com/tspeterkim)
3 points by tspeterkim on April 14, 2024 | past
Show HN: Flash Attention in ~100 lines of CUDA (github.com/tspeterkim)
230 points by tspeterkim on March 16, 2024 | past | 39 comments

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

Search: