Revert "Use LazyValue for routed_experts_weights_of_layer initialization"#161
Merged
Hexq0210 merged 4 commits intoAscend:release/PoC_20260331from Mar 28, 2026
Merged
Revert "Use LazyValue for routed_experts_weights_of_layer initialization"#161Hexq0210 merged 4 commits intoAscend:release/PoC_20260331from
Hexq0210 merged 4 commits intoAscend:release/PoC_20260331from
Conversation
CLA Signature Guide@longxin9715 , thanks for your pull request. The following commit(s) are not associated with a signed Contributor License Agreement (CLA).
To sign CLA, click here. To check if your email is configured correctly, refer to the FAQs. Once you've signed the CLA or updating your email, please comment |
iforgetmyname
previously approved these changes
Mar 28, 2026
added 2 commits
March 28, 2026 17:53
* origin/main: [MLX] Add native MLX execution backend for Apple Silicon Mac (sgl-project#20342) [Diffusion] Refactor diffusion JIT kernel test layout and narrow CI triggers (sgl-project#21385) [CI] Add PID namespace and ps auxf diagnostics to killall.py (sgl-project#21401)
CLA Signature Guide@longxin9715 , thanks for your pull request. The following commit(s) are not associated with a signed Contributor License Agreement (CLA).
To sign CLA, click here. To check if your email is configured correctly, refer to the FAQs. Once you've signed the CLA or updating your email, please comment |
iforgetmyname
approved these changes
Mar 28, 2026
Hexq0210
approved these changes
Mar 28, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Title
Revert "Use LazyValue for routed_experts_weights_of_layer initialization"
Motivation
Original PR :sgl-project#15904
Revert the modification of wrapping
routed_experts_weights_of_layerwith LazyValue.After using LazyValue, the expert load balancing logic fails to execute correctly, causing runtime errors in MoE expert scheduling and load balancing.
Restore the original direct initialization to ensure normal operation of expert load balancing.
Modifications
routed_experts_weights_of_layerassignment logicLazyValuewrapper and lambda expressionAccuracy Tests
N/A
Pure logic revert, no impact on model accuracy and output results.
Benchmarking and Profiling
N/A
No inference performance changes introduced.
Checklist
Review Process
/tag-run-ci-label,/rerun-failed-ci,/tag-and-rerun-ci