AlpinDale ccbda97416 fix: types in AQLM and GGUF for dynamo support (#736) 3 месяцев назад
..
all_reduce f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
attention f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
backup f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 9 месяцев назад
core 9296d4b25d feat: dynamo support for ScalarType (#733) 3 месяцев назад
cpu f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
hadamard 5d288aa76c feat: add fast hadamard transformation kernels (#232) 11 месяцев назад
mamba f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
moe f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
prepare_inputs f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
punica f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
quantization ccbda97416 fix: types in AQLM and GGUF for dynamo support (#736) 3 месяцев назад
activation_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
cache.h f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
cache_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
cuda_compat.h f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
cuda_utils.h f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
cuda_utils_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
dispatch_utils.h f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
layernorm_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
ops.h f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
pos_encoding_kernels.cu f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
reduction.cuh f1d0b77c92 [0.6.0] Release Candidate (#481) 4 месяцев назад
torch_bindings.cpp a401f8e05d feat: per-tensor token epilogue kernels (#630) 4 месяцев назад