SqueezeLLM: Lossless 3-bit quantization with improved performance (arxiv.org)

4 points by vegarab 3y ago ↗ HN

0 comments

[ 2.8 ms ] story [ 26.2 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats