LLM Inference in pure Java with a GPU acceleration enabled (github.com)

3 points by mikepapadim 1y ago ↗ HN

0 comments

[ 1.9 ms ] story [ 7.6 ms ] thread

No comments yet.

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

Source · Live DB stats