AlpinDale 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
..
attention 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
quantization 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
activation_kernels.cu 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
cache.h 1aab8a7d6f feat: speedup compilation times by 3x (#130) пре 1 година
cache_kernels.cu 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
cuda_compat.h 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
cuda_utils.h 1aab8a7d6f feat: speedup compilation times by 3x (#130) пре 1 година
cuda_utils_kernels.cu 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
dispatch_utils.h 32844c1522 add GELU kernels and remove compile bloat пре 1 година
layernorm_kernels.cu 7612f33afd feat: fused add RMSNorm kernels (#125) пре 1 година
ops.h 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
pos_encoding_kernels.cu 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
pybind.cpp 1334a833a4 feat: AMD ROCm support (#95) пре 1 година
reduction.cuh 1334a833a4 feat: AMD ROCm support (#95) пре 1 година