DeepSeek-V4-Flash means LLM steering is interesting again(seangoedecke.com)210 points by Brajeshwar 5 months ago | 67 comments
Speculative KV coding: losslessly compressing KV cache by up to ~4×(fergusfinn.com)137 points by kkm 4 months ago | 28 comments
Release of Fugaku-LLM – a large language model trained on supercomputer Fugaku(fujitsu.com)89 points by gslin 2 years ago | 31 comments
LLMs could be, but shouldn't be compilers(alperenkeles.com)104 points by alpaylan 8 months ago | 112 comments