【LLM Inference-0】Add Split MoE Op && Add Group MoE #69687
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
你的PR提交成功，感谢你对开源项目的贡献! |
gzy19990617
force-pushed
the
add_group_moe
branch
4 times, most recently
from
91d85bb to
316e922
Compare
gzy19990617
force-pushed
the
add_group_moe
branch
from
316e922 to
5bba5a3
Compare
gzy19990617
changed the title
gzy19990617
force-pushed
the
add_group_moe
branch
from
bc58f6d to
66d6660
Compare
gzy19990617
force-pushed
the
add_group_moe
branch
from
2db7763 to
8769e56
Compare
|
|
|
Sorry to inform you that f52f14b's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
gzy19990617
changed the title
|
Sorry to inform you that 79d7e73's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Category
Inference
PR Types
Others
Description
card-71500
1.增加拆分的moe算子，更便于做精度对齐，将分组softmax操作合并到一个moe_dispatch算子之中，精度已对齐。
2.增加group_moe功能的支持，新增group_moe接口。
3.补充group moe下的拆分算子的精度单测
4.补充拆分算子与之前baseline不同精度的单测