Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression (zartbot.github.io)
125 points by mfiguiere 15 hours ago | past | 10 comments
On Next-Gen Transformer: Loops Are Not What You Need (zartbot.github.io)
26 points by matt_d 6 days ago | past | 1 comment
Redesigning the Inference Chip (zartbot.github.io)
1 point by __patchbit__ 17 days ago | past
Redesigning the Inference Chip: From Nvidia GPU's Flaws to OpenAI JalapeƱo (zartbot.github.io)
5 points by hasheddan 18 days ago | past
Dissecting the SM_120 Microarchitecture (zartbot.github.io)
2 points by hasheddan 3 months ago | past

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

Search: