cuda : fix dmmv cols requirement to 2*GGML_CUDA_DMMV_X (#8800)
* cuda : fix dmmv cols requirement to 2*GGML_CUDA_DMMV_X * update asserts * only use dmmv for supported types * add test
S
slaren committed
7a11eb3a260915aee16101808f291a244e2facc7
Parent: c8a0090
Committed by GitHub <noreply@github.com>
on 8/1/2024, 1:26:22 PM