text-generation-inference/server/marlin/marlin_kernels/sparse/common
Daniël de Kok 4700ea413f Add support for Marlin 2:4 sparsity (#2102)
This change adds support for 2:4 sparsity when using Marlin
quantization. The 2:4 kernel is used when:

* The quantizer is `marlin`;
* the quantizer checkpoint format is `marlin_24`.

Fixes #2098.
2024-09-24 03:55:04 +00:00
..
base.h Add support for Marlin 2:4 sparsity (#2102) 2024-09-24 03:55:04 +00:00
mem.h Add support for Marlin 2:4 sparsity (#2102) 2024-09-24 03:55:04 +00:00
mma.h Add support for Marlin 2:4 sparsity (#2102) 2024-09-24 03:55:04 +00:00