Set Block Decoding Is a Language Model Inference Accelerator (arxiv.org)

4 points by veryluckyxyz 1y ago ↗ HN

0 comments

[ 3.1 ms ] story [ 22.7 ms ] thread

No comments yet.

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

Source · Live DB stats