WINA: Weight informed Neuron activation for accelerating LLM inference | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

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

2 points by Ratelman 350 days ago | 0 comments

No comments yet

WINA: Weight informed Neuron activation for accelerating LLM inference | Dark Hacker News