3 projects
VeloxQuant-MLX
Fast KV cache quantization for Apple Silicon — TurboQuant, RVQ, VecInfer (with Metal kernels), RateQuant, PolarQuant, SpectralQuant, CommVQ, RaBitQ, QJL, KIVI, KIVI-Sink, SVDq, Kitty, AdaKV-proxy, XQuant, KVQuant-NUQ, PALU, CacheGen, MiniCache, GEAR, ZipCache-adapted, SnapKV-adapted, StreamingLLM-adapted, H2O-adapted, TOVA-adapted, PyramidKV-adapted, SqueezeAttention-adapted, ChunkKV-adapted, CaM-adapted, and xKV-adapted in MLX
callflow-tracer
A lightweight Python library for tracing function call relationships and visualizing them as interactive graphs, anomaly detection, and OpenTelemetry export for production observability
pyguard-ai
AI-powered PyPI supply chain security scanner
