mirror of https://github.com/hpcaitech/ColossalAI
aibig-modeldata-parallelismdeep-learningdistributed-computingfoundation-modelsheterogeneous-traininghpcinferencelarge-scalemodel-parallelismpipeline-parallelism
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
36 lines
1.1 KiB
36 lines
1.1 KiB
from .cpu_adam import CpuAdamArmExtension, CpuAdamX86Extension |
|
from .flash_attention import ( |
|
FlashAttentionDaoCudaExtension, |
|
FlashAttentionNpuExtension, |
|
FlashAttentionXformersCudaExtension, |
|
) |
|
from .layernorm import LayerNormCudaExtension |
|
from .moe import MoeCudaExtension |
|
from .optimizer import FusedOptimizerCudaExtension |
|
from .softmax import ScaledMaskedSoftmaxCudaExtension, ScaledUpperTriangleMaskedSoftmaxCudaExtension |
|
|
|
ALL_EXTENSIONS = [ |
|
CpuAdamArmExtension, |
|
CpuAdamX86Extension, |
|
LayerNormCudaExtension, |
|
MoeCudaExtension, |
|
FusedOptimizerCudaExtension, |
|
ScaledMaskedSoftmaxCudaExtension, |
|
ScaledUpperTriangleMaskedSoftmaxCudaExtension, |
|
FlashAttentionDaoCudaExtension, |
|
FlashAttentionXformersCudaExtension, |
|
FlashAttentionNpuExtension, |
|
] |
|
|
|
__all__ = [ |
|
"CpuAdamArmExtension", |
|
"CpuAdamX86Extension", |
|
"LayerNormCudaExtension", |
|
"MoeCudaExtension", |
|
"FusedOptimizerCudaExtension", |
|
"ScaledMaskedSoftmaxCudaExtension", |
|
"ScaledUpperTriangleMaskedSoftmaxCudaExtension", |
|
"FlashAttentionDaoCudaExtension", |
|
"FlashAttentionXformersCudaExtension", |
|
"FlashAttentionNpuExtension", |
|
]
|
|
|