The gap between open weights LLMs and closed source LLMs 26 days agothis is a blog post from a company that hosts open weights LLMs (https://www.doubleword.ai/). I think its possible it might have been tongue in cheek 0ThreadHN
The Economics of Speculative Decoding 1 month agohttps://fergusfinn.com/blog/economics-of-speculative-decodin...good point tho - plus for Deepseek the shared expert increases the overlap slightly 0ThreadHN
Speculative KV coding: losslessly compressing KV cache by up to ~4× 2 months agotrue, but no reason the predictor model couldn't use linear attention (i.e. mamba, GDN etc) to predict KV caches 0ThreadHN