News for hackers. Stuff that matters.

A comment on Lossless LLM compression for efficient GPU inference via dynamic-length float.

Re:Lossless LLM compression for efficient GPU inference via ... by aazo11 on Friday April 25, 2025 @05:58PM (#43798917)
This is a huge unlock for on-device inference. The download time of larger models makes local inference unusable for non-technical users.
[ Parent | on HN ]

There are no comments on this comment yet.