[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)

* 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
This commit is contained in:
傅剑寒
2024-04-24 14:17:54 +08:00
committed by GitHub
parent 04863a9b14
commit 279300dc5f
64 changed files with 345 additions and 310 deletions

View File

@@ -35,7 +35,7 @@ from transformers.utils import (
replace_return_docstrings,
)
from colossalai.kernel.extensions.flash_attention import HAS_FLASH_ATTN
from colossalai.kernel.extensions.pybind.flash_attention import HAS_FLASH_ATTN
from colossalai.kernel.triton.llama_act_combine_kernel import HAS_TRITON
from colossalai.moe.layers import SparseMLP
from colossalai.moe.manager import MOE_MANAGER