Ideas & society2025 · shared on Hacker News
Lossless LLM compression for efficient GPU inference via dynamic-length float
Explore Lossless LLM compression for efficient GPU inference via dynamic-length float, 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.
YCharlesW ·
Lossless LLM compression for efficient GPU inference via dynamic-length float
411 points117 comments