mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-22 15:32:08 +00:00
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. |
||
---|---|---|
.. | ||
common | ||
marlin_24_cuda_kernel.cu |