marcsun13
/

ggml-quantization

Model card Files Files and versions

ggml-quantization / flake.nix

Commit History

vendor only the files the build reaches

091adac

Marc Sun commited on 16 days ago

GGUF kernels: dequantize + fused gemv over packed blocks

f79d690
verified

marcsun13 HF Staff commited on Aug 5

GGUF kernels: dequantize + fused gemv over packed blocks

97231ed
verified

marcsun13 HF Staff commited on Aug 5

GGUF kernels: dequantize + fused gemv over packed blocks, 9 CUDA variants

2c20074
verified

marcsun13 HF Staff commited on Aug 5