CUDA: refactor and optimize IQ MMVQ (#8215)
* CUDA: refactor and optimize IQ MMVQ * uint -> uint32_t * __dp4a -> ggml_cuda_dp4a * remove MIN_CC_DP4A checks * change default * try CI fix
J
Johannes Gäßler committed
cb5fad4c6c2cbef92e9b8b63449e1cb7664e4846
Parent: dae57a1
Committed by GitHub <noreply@github.com>
on 7/1/2024, 6:39:06 PM