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