tanishqkumar/ssd

A lightweight inference engine supporting speculative speculative decoding (SSD).

1 best points · 0 comments · 1 Hacker News post · 1,019 GitHub stars · View on GitHub

Hacker News discussions

• Speculative Speculative Decoding: Really, Really Fast LLM Inference (1 points, 0 comments, by fizzbuzz07, 2026-03-04)