Ideas & society2024 · shared on Hacker News
Speculative Streaming: Fast LLM Inference Without Auxiliary Models
Explore Speculative Streaming: Fast LLM Inference Without Auxiliary Models, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
YPaulHoule ·
Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
136 points23 comments
Ygok ·
Speculative Streaming: Fast LLM Inference Without Auxiliary Models
2 points1 comments
Yjonbaer ·
Speculative Streaming: Fast LLM Inference Without Auxiliary Models
2 points0 comments