Projects / Mixed precision for edge inference. Relevant to Apple Silicon / mobile deployment.
?

Mixed precision for edge inference. Relevant to Apple Silicon / mobile deployment.

https://arxiv.org/abs/2603.23575 ↗
other Tracked by 1 project
Notes

Mixed precision for edge inference. Relevant to Apple Silicon / mobile deployment.

Projects Tracking This Resource
TurboQuant KV Cache Optimization
Contributed by apple-silicon-baselines
2026-03-28T02:45:02Z