Back to trending
W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.
Python426 stars25 forksMIT
apple-siliconmetalmlxquantizationw4a8w8a8
Rankings
Daily
#5587
0
Weekly
#9480
0
Monthly
—
Engagement
Total stars
Daily new stars
Get badge
Add a Trending Repos badge to your README
This repository is tracked by Trending Repos. The badge upgrades automatically the moment it cracks the top 100 — set it once and forget it.
Markdown — paste into your README
[](https://trending-repos.com/repositories/Mininglamp-AI/cider)HTML
<a href="https://trending-repos.com/repositories/Mininglamp-AI/cider"><img src="https://trending-repos.com/badge/Mininglamp-AI/cider.svg" alt="Trending Repos" /></a>Raw image URL
https://trending-repos.com/badge/Mininglamp-AI/cider.svg