Accelerating LLM Inference with Parallel Draft Models (PARD) (amd.com)

1 points by dhruvdh 1y ago ↗ HN

0 comments

[ 3.7 ms ] story [ 13.5 ms ] thread

No comments yet.

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

Source · Live DB stats