fix: Reduce memory usage in fused moe op associated with AutoTuning. #3783
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
Collaborator
hyukn
commented
Apr 23, 2025
hyukn
commented
- Replace the pre-defined bucket sizes with a generating function based on the tune_max_num_tokens in fused moe op tuning.
- Add free_memory logic of workspace in min_latency_mode fused moe path.
* Replace pre-defined bucket size strategy with a generating function based on the tune_max_num_tokens. * Add free_memory logic of workspace in min_latency_mode fused moe path. Signed-off-by: Yukun He <[email protected]>
|
/bot run |
hyukn
changed the title
|
PR_Github #3119 [ run ] triggered by Bot |
|
/bot kill |
|
Retarget to release/0.19 with this PR #3793. |
|
PR_Github #3119 [ run ] completed with state |
|
/bot kill |
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Outdated suggestions cannot be applied.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.