Skip to content

[CUDA] New 4bit GEMM kernels for inference#1949

Open
matthewdouglas wants to merge 7 commits into
mainfrom
gemm4bit
Open

[CUDA] New 4bit GEMM kernels for inference#1949
matthewdouglas wants to merge 7 commits into
mainfrom
gemm4bit

Commits

Commits on May 15, 2026