[common] merge ChatGLM2Attention::forward into Attention::forward #86
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
add epsilon param into LayerNorm to align with RmsNorm (LayerNorm doesn't use this param) extend qk_shape from 4 to 5 in attention.h, to pass key_head_num into rotary_embedding_chatglm2 for multi-query-attention.
a3213105
changed the title
|
Please rebase to the main and fix the conflicts. |
done |
Duyi-Wang
approved these changes
Dec 1, 2023
abenmao
pushed a commit
to abenmao/xFasterTransformer
that referenced
this pull request
Dec 4, 2023
add epsilon param into LayerNorm to align with RmsNorm (LayerNorm doesn't use this param) extend qk_shape from 4 to 5 in attention.h, to pass key_head_num into rotary_embedding_chatglm2 for multi-query-attention.
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Outdated suggestions cannot be applied.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.
add epsilon param into LayerNorm to align with RmsNorm to unify Norm APIs (LayerNorm doesn't use this param)
extend qk_shape from 4 to 5 in attention.h, to pass key_head_num which is needed by rotary_embedding_chatglm2 for multi-query-attention.