marcsun13
/

ggml-quantization

Model card Files Files and versions

ggml-quantization / vendor

404 kB

Ctrl+K

Ctrl+K

2 contributors

History: 4 commits

Marc Sun

add mul_mat_id, and compile upstream's kernels as they ship

9534e0b 12 days ago

src
add mul_mat_id, and compile upstream's kernels as they ship 12 days ago
LICENSE
1.08 kB
GGUF kernels: dequantize + fused gemv over packed blocks, 9 CUDA variants about 1 month ago
UPSTREAM
79 Bytes
add mul_mat_id, and compile upstream's kernels as they ship 12 days ago