Enable mixed scan strategy for models with Engram#3255
Merged
copybara-service[bot] merged 1 commit intomainfrom Mar 5, 2026
Merged
Enable mixed scan strategy for models with Engram#3255copybara-service[bot] merged 1 commit intomainfrom
copybara-service[bot] merged 1 commit intomainfrom
Conversation
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
3c2e251 to
3654d6d
Compare
gobbleturk
reviewed
Mar 2, 2026
b7d17e0 to
c53574e
Compare
|
🤖 Hi @RissyRan, I've received your request, and I'm working on it now! You can track my progress in the logs for more details. |
|
🤖 I'm sorry @RissyRan, but I was unable to process your request. Please see the logs for more details. |
c8c3ba0 to
9cfd551
Compare
gagika
reviewed
Mar 5, 2026
Collaborator
gagika
left a comment
There was a problem hiding this comment.
the logic looks good to me.
could you try to do through a helper function and some code re-use?
9cfd551 to
fe34076
Compare
fe34076 to
84eed11
Compare
RissyRan
commented
Mar 5, 2026
3da6bda to
33d4d22
Compare
33d4d22 to
6c94aa2
Compare
6c94aa2 to
88afe99
Compare
gobbleturk
approved these changes
Mar 5, 2026
gagika
approved these changes
Mar 5, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Refactor and enable scan for DeepSeek custom model with Engram layers, config link
Due to challenges with random layer IDs across the entire scan block, the model is currently partitioned segments in order. For instance, we have 10 layers, and first 5 as Dense, and last 5 as MoE, and Engram is at 3rd, and 9th.
Tests
deepseek_scan_engram_test.py, and expect to passdeepseek-custom, max_target_length=4096 per_device_batch_size=16on v5p) link - Obvious performance gains and reduced memory footprint.Checklist
Before submitting this PR, please make sure (put X in square brackets):
gemini-reviewlabel.