Skip to content

cuda: fuse SwiGLU + sign flip + Hadamard (and the PTQ1_0 MMQ q8_1 quantization) for prompt batches - #445

Open
sb32445 wants to merge 1 commit into
PrismML-Eng:prismfrom
sb32445:pr/swiglu-hadamard-prefill
Open

sb32445 wants to merge 1 commit into
PrismML-Eng:prismfrom
sb32445:pr/swiglu-hadamard-prefill

cuda: fuse SwiGLU + sign flip + Hadamard transform for PTQ1_0 prompt …

6d837bb
Select commit
Loading
Failed to load commit list.