Fusing a 27B ternary LLM's whole decode step into one CUDA kernel
By Jr23_xd · 2026-07-16 · 1 points · 0 comments
https://twitter.com/Akashi203/status/2077552491567157733
By Jr23_xd · 1 points · 0 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews