00:39
2026-07-16
twitter.com
artificial-intelligence
Fusing a 27B ternary LLM's whole decode step into one CUDA kernel
RightNow AI open-sourced bonsai-turbo, a batch-1 decode engine that runs PrismML's Bonsai 27B ternary LLM 1.76x faster than the official llama.cpp fork on an H100, achieving 151 tok/s (ternary) and 15…