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.
39 lines
1.3 KiB
39 lines
1.3 KiB
from .pybind.cpu_adam import CpuAdamArmExtension, CpuAdamX86Extension |
|
from .pybind.flash_attention import ( |
|
FlashAttentionDaoCudaExtension, |
|
FlashAttentionNpuExtension, |
|
FlashAttentionSdpaCudaExtension, |
|
) |
|
from .pybind.inference import InferenceOpsCudaExtension |
|
from .pybind.layernorm import LayerNormCudaExtension |
|
from .pybind.moe import MoeCudaExtension |
|
from .pybind.optimizer import FusedOptimizerCudaExtension |
|
from .pybind.softmax import ScaledMaskedSoftmaxCudaExtension, ScaledUpperTriangleMaskedSoftmaxCudaExtension |
|
|
|
ALL_EXTENSIONS = [ |
|
CpuAdamArmExtension, |
|
CpuAdamX86Extension, |
|
LayerNormCudaExtension, |
|
MoeCudaExtension, |
|
FusedOptimizerCudaExtension, |
|
InferenceOpsCudaExtension, |
|
ScaledMaskedSoftmaxCudaExtension, |
|
ScaledUpperTriangleMaskedSoftmaxCudaExtension, |
|
FlashAttentionDaoCudaExtension, |
|
FlashAttentionSdpaCudaExtension, |
|
FlashAttentionNpuExtension, |
|
] |
|
|
|
__all__ = [ |
|
"CpuAdamArmExtension", |
|
"CpuAdamX86Extension", |
|
"LayerNormCudaExtension", |
|
"MoeCudaExtension", |
|
"FusedOptimizerCudaExtension", |
|
"InferenceOpsCudaExtension", |
|
"ScaledMaskedSoftmaxCudaExtension", |
|
"ScaledUpperTriangleMaskedSoftmaxCudaExtension", |
|
"FlashAttentionDaoCudaExtension", |
|
"FlashAttentionSdpaCudaExtension", |
|
"FlashAttentionNpuExtension", |
|
]
|
|
|