WINA: Weight informed Neuron activation for accelerating LLM inference (arxiv.org)

2 points by Ratelman 1y ago ↗ HN

0 comments

[ 2.4 ms ] story [ 6.7 ms ] thread

No comments yet.

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

Source · Live DB stats