mscheong01/speculative_decoding.c

minimal C implementation of speculative decoding based on llama2.c

2 best points · 0 comments · 1 Hacker News post · 30 GitHub stars · View on GitHub

Hacker News discussions

• Speculative decoding of llama2 models in pure C (2 points, 0 comments, by mscheong, 2024-04-22)