Make fused QKV projection the default implementation - #4546
Open
anijain2305 wants to merge 5 commits into
Open
Conversation
anijain2305
requested review from
fegin,
tianyu-l,
wconstab and
wwwjn
as code owners
September 9, 2026 18:03
meta-cla
Bot
added
the
CLA Signed
anijain2305
marked this pull request as draft
September 9, 2026 18:04
anijain2305
marked this pull request as ready for review
September 9, 2026 18:06
This was referenced Sep 9, 2026
tianyu-l
approved these changes
Sep 9, 2026
| f"set_qkv_linear_sharding requires QKVLinear.Config or " | ||
| f"FusedQKVLinear.Config, got {type(qkv_linear_cfg).__name__}" | ||
| ) | ||
| def set_fused_qkv_linear_sharding(qkv_linear_cfg: FusedQKVLinear.Config) -> None: |
Contributor
There was a problem hiding this comment.
don't need this function any more
|
|
||
|
|
||
| class FusedQKVLinear(BaseQKVLinear): | ||
| class FusedQKVLinear(Module): |
Contributor
There was a problem hiding this comment.
I wonder if we should call it QKVLinear to be consistent with FeedForward. After all, we don't have "unfused" version any more.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack from ghstack (oldest at bottom):