github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-07 03:52:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

[hotfix] moe hybrid parallelism benchmark & follow-up fix (#6048)

Browse Source 
* [example] pass use_fp8_comm flag to all plugins

* [example] add mixtral benchmark

* [moe] refine assertion and check

* [moe] fix mixtral & add more tests

* [moe] consider checking dp * sp group and moe_dp_group

* [mixtral] remove gate tp & add more tests

* [deepseek] fix tp & sp for deepseek

* [mixtral] minor fix

* [deepseek] add deepseek benchmark
This commit is contained in:
botbw
2024-09-10 17:30:53 +08:00
committed by GitHub
parent 8fd25d6e09
commit c54c4fcd15
21 changed files with 907 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
colossalai/shardformer/modeling/mixtral.py
View File

@@ -36,7 +36,7 @@ from colossalai.shardformer.layer._operation import (
gather_forward_split_backward,
split_forward_gather_backward,
)
from colossalai.shardformer.layer.linear import Linear1D_Col, Linear1D_Row
from colossalai.shardformer.layer.linear import Linear1D_Col, Linear1D_Row, ParallelModule
from colossalai.shardformer.shard import ShardConfig
from colossalai.shardformer.shard.utils import set_tensors_to_none
from colossalai.tensor.moe_tensor.api import set_moe_tensor_ep_group
@@ -49,7 +49,7 @@ if is_flash_attn_2_available():
_flash_supports_window_size = "window_size" in list(inspect.signature(flash_attn_func).parameters)
class EPMixtralSparseMoeBlock(MixtralSparseMoeBlock):
class EPMixtralSparseMoeBlock(ParallelModule):
def __init__(self, *args, **kwargs):
raise RuntimeError(f"Please use `from_native_module` to create an instance of {self.__class__.__name__}")