rajveer43

rajveer43/VeloxQuant-MLX

implementation for Apple Silicon Faster KV cache quantization optimized for MLX

11 stars 3 forks 11 watchers Python MIT License

kv kv-cache llm macos macos-package mlx ondeviceai ondevicemachinelearning quantization

View on GitHub Website

2 Open Issues Need Help Last updated: Aug 3, 2026

Open Issues Need Help

View All on GitHub

P0: mlx-lm used throughout but not declared as a dependency in pyproject.toml about 2 hours ago

bug good first issue

rajveer43/VeloxQuant-MLX

11

implementation for Apple Silicon Faster KV cache quantization optimized for MLX

Python

#kv#kv-cache#llm#macos#macos-package#mlx#ondeviceai#ondevicemachinelearning#quantization

P0: Fix broken Netlify quickstart — uses nonexistent APIs (bits=, KVCacheBuilder.build, kv_cache=, MemoryObserver.attach) about 2 hours ago

bug good first issue

rajveer43/VeloxQuant-MLX

11

implementation for Apple Silicon Faster KV cache quantization optimized for MLX

Python

#kv#kv-cache#llm#macos#macos-package#mlx#ondeviceai#ondevicemachinelearning#quantization