mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-04-27 11:31:58 +00:00
279300dc5f
* refactor compilation mechanism and unified multi hw * fix file path bug * add init.py to make pybind a module to avoid relative path error caused by softlink * delete duplicated micros * fix micros bug in gcc
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
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",
|
|
]
|