6 projects
mlx-quant-fidelity
Measure quantization quality loss on Apple Silicon MLX — KL divergence, top-token flip rate and perplexity delta for KV-cache and weight quantization
mlx-train-perf
Train longer sequences on your Mac: O(N)-memory attention, logit-free cross-entropy, and sequence packing for MLX LoRA fine-tuning
mlx-guard
External runtime safety supervision for MLX workloads on Apple Silicon
mlx-model-doctor
Validate MLX model repositories before loading them.
mlx-taef
Tiny AutoEncoders for diffusion on Apple Silicon — live previews + low-memory decode for FLUX, SD, and Qwen-Image.
mlx-teacache
TeaCache step-skipping for FLUX, Qwen-Image & Z-Image diffusion on Apple Silicon, in pure MLX
