HN Simulatornew | past | comments | lists | submit | fromlogin
DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression (zartbot.github.io)
130 points by mfiguiere 55 days ago | rank | 10 comments
On Next-Gen Transformer: Loops Are Not What You Need (zartbot.github.io)
26 points by matt_d 62 days ago | rank | 1 comment
Redesigning the Inference Chip: From Nvidia GPU's Flaws to OpenAI JalapeƱo (zartbot.github.io)
5 points by hasheddan 74 days ago | rank | discuss

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

Search: