Profiling LLM Inference on Apple Silicon: A Quantization Perspective (arxiv.org)

2 points by diggan 1y ago ↗ HN

0 comments

[ 0.21 ms ] story [ 16.3 ms ] thread

No comments yet.

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

Source · Live DB stats