Fuse split rotary for Group Query Attention #940
Merged
Conversation
This file contains hidden or 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
|
CC @masahi as the original author of this optimization :) |
|
|
||
| return split_rotary | ||
|
|
||
| def get_split_rotary_group_query_attention(num_query_heads, num_kv_heads, head_dim, position_embedding_base): |
There was a problem hiding this comment.
I’m wondering if we can merge the two get_split_rotary into one.
There was a problem hiding this comment.
We fuse split rotary of GQA into 2 kernels because of num_heads are different, while split rotary of non-GQA is fused into 1 kernel. So let's keep them as different function
|
nice, does a big model that use MQA / GQA benefit from this pass? The speed up for 13B was much smaller than 7B when I tested. |
|
llama2 70b uses GQA. Indeed the speed up is small. Only 2% I observed |
MasterJH5574
approved these changes
Sep 19, 2023
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Outdated suggestions cannot be applied.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.
No description provided.