.. |
adagrad
|
c1ba6a104f
[CANN] Support cpu offload optimizer for Ascend NPU (#4568)
|
11 months ago |
adam
|
9b6ef9e1f0
64bit indexing fused adam (#5187)
|
6 months ago |
aio
|
0d9cfa01e2
[NPU]ZeRO-Infinity feature compatibility (#5077)
|
8 months ago |
common
|
b361c72761
Update DeepSpeed copyright license to Apache 2.0 (#3111)
|
1 year ago |
cpu
|
b22706a721
[CPU] Support SHM based inference_all_reduce in TorchBackend (#5391)
|
6 months ago |
deepspeed4science
|
1d1a20c5a1
Fix the openfold training. (#4657)
|
11 months ago |
fp_quantizer
|
c632ea09f8
Selective dequantization (#5375)
|
6 months ago |
includes
|
3fbd01ccca
FP [6,8,12] quantizer op (#5336)
|
6 months ago |
lamb
|
c7724c6181
Switch from HIP_PLATFORM_HCC to HIP_PLATFORM_AMD (#4539)
|
1 year ago |
lion
|
c1ba6a104f
[CANN] Support cpu offload optimizer for Ascend NPU (#4568)
|
11 months ago |
quantization
|
c7724c6181
Switch from HIP_PLATFORM_HCC to HIP_PLATFORM_AMD (#4539)
|
1 year ago |
random_ltd
|
c7724c6181
Switch from HIP_PLATFORM_HCC to HIP_PLATFORM_AMD (#4539)
|
1 year ago |
sparse_attention
|
b361c72761
Update DeepSpeed copyright license to Apache 2.0 (#3111)
|
1 year ago |
spatial
|
c7724c6181
Switch from HIP_PLATFORM_HCC to HIP_PLATFORM_AMD (#4539)
|
1 year ago |
transformer
|
38b41dffa1
DeepSpeed-FastGen (#4604)
|
11 months ago |
utils
|
b361c72761
Update DeepSpeed copyright license to Apache 2.0 (#3111)
|
1 year ago |
xpu
|
f4f31317ed
[XPU] XPU accelerator support for Intel GPU device (#4547)
|
9 months ago |