.. |
all_reduce
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
attention
|
0256ed236b
feat: windows support (#790)
|
2 mesiacov pred |
backup
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 mesiacov pred |
core
|
0256ed236b
feat: windows support (#790)
|
2 mesiacov pred |
cpu
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
hadamard
|
5d288aa76c
feat: add fast hadamard transformation kernels (#232)
|
11 mesiacov pred |
mamba
|
0256ed236b
feat: windows support (#790)
|
2 mesiacov pred |
moe
|
0256ed236b
feat: windows support (#790)
|
2 mesiacov pred |
prepare_inputs
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
punica
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
quantization
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
2 mesiacov pred |
sampling
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
1 mesiac pred |
activation_kernels.cu
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
cache.h
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
cache_kernels.cu
|
0256ed236b
feat: windows support (#790)
|
2 mesiacov pred |
cuda_compat.h
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
cuda_utils.h
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
cuda_utils_kernels.cu
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
dispatch_utils.h
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
layernorm_kernels.cu
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
ops.h
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
1 mesiac pred |
pos_encoding_kernels.cu
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesiacov pred |
reduction.cuh
|
0256ed236b
feat: windows support (#790)
|
2 mesiacov pred |
torch_bindings.cpp
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
1 mesiac pred |