Compiler optimizations for 5.8ms GPT-OSS-120B inference (not on GPUs) (furiosa.ai)

9 points by olibaw 11mo ago ↗ HN

0 comments

[ 6390 ms ] story [ 73.2 ms ] thread

No comments yet.

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

Source · Live DB stats