AlpinDale d91e4e98e1 attempt adding kernels back 1 miesiąc temu
..
all_reduce f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
attention f831fd8312 rocm: fix compile issues with rocm 6.2 (#893) 1 miesiąc temu
backup f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 10 miesięcy temu
core 0256ed236b feat: windows support (#790) 3 miesięcy temu
cpu f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
cutlass_extensions 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 2 miesięcy temu
hadamard d91e4e98e1 attempt adding kernels back 1 miesiąc temu
mamba 0256ed236b feat: windows support (#790) 3 miesięcy temu
moe 0256ed236b feat: windows support (#790) 3 miesięcy temu
prepare_inputs f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
punica f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
quantization 2a60b8f8c9 kernel: do not compile machete for cuda 11 and below (#901) 1 miesiąc temu
sampling bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828) 2 miesięcy temu
activation_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
cache.h f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
cache_kernels.cu 0256ed236b feat: windows support (#790) 3 miesięcy temu
cuda_compat.h f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
cuda_utils.h 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 2 miesięcy temu
cuda_utils_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
dispatch_utils.h f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
layernorm_kernels.cu e14223dce5 kernel: use `cub::BlockReduce` instead of custom impl (#895) 1 miesiąc temu
ops.h 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 2 miesięcy temu
permute_cols.cu 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 2 miesięcy temu
pos_encoding_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 5 miesięcy temu
torch_bindings.cpp 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 2 miesięcy temu