AlpinDale 6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689) vor 4 Monaten
..
all_reduce f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
attention f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
backup f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) vor 9 Monaten
core 6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689) vor 4 Monaten
cpu f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
hadamard 5d288aa76c feat: add fast hadamard transformation kernels (#232) vor 11 Monaten
mamba f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
moe f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
prepare_inputs f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
punica f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
quantization 6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689) vor 4 Monaten
activation_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
cache.h f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
cache_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
cuda_compat.h f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
cuda_utils.h f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
cuda_utils_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
dispatch_utils.h f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
layernorm_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
ops.h f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
pos_encoding_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
reduction.cuh f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
torch_bindings.cpp a401f8e05d feat: per-tensor token epilogue kernels (#630) vor 4 Monaten