MegaScale: Scaling Large Language Model Training to More Than 10k GPUs [pdf] (usenix.org)

1 points by yankcrime 1y ago ↗ HN

0 comments

[ 3.1 ms ] story [ 7.2 ms ] thread

No comments yet.

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

Source · Live DB stats