FP8: Efficient model inference with 8-bit floating point numbers (baseten.co)

2 points by philipkiely 2y ago ↗ HN

0 comments

[ 1.8 ms ] story [ 12.3 ms ] thread

No comments yet.

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

Source · Live DB stats