VeloxQuant-MLX 0.91.4

T1Covered by 1 source · first reported by PyPI / crates.io / RubyGems / Go index / NuGet at 24 Sept, 17:33 UTC

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods, from TurboQuant and KIVI to A2ATS, with Metal kernels

releases

Sources

• T1VeloxQuant-MLX 0.91.4PyPI / crates.io / RubyGems / Go index / NuGet24 Sept, 17:33