[Diffusion] Revert CPU AMX optimizations - #30716
Merged
Merged
Conversation
…gl-project#28527)" This reverts commit 177c048.
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
github-actions
Bot
added
Multi-modal
mickqian
marked this pull request as ready for review
July 10, 2026 01:03
mickqian
requested review from
AgainstEntropy,
BBuf,
FlamingoPg,
HaiShaw,
ispobock,
merrymercy,
ping1jing2,
yhyang201,
yichiche,
yingluosanqian,
yizhang2077 and
yuan-luo
as code owners
July 10, 2026 01:03
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
Author
|
@mingfeima, please make sure all nvidia multimodal-gen tests (call-multimodal-gen-tests) pass before merging. Join me in making the CI more stable and pushing SGLang-Diffusion forward. |
Collaborator
Author
|
/tag-and-rerun-ci |
BBuf
approved these changes
Jul 10, 2026
Chronostasys
pushed a commit
to MindLab-Research/sglang
that referenced
this pull request
Aug 24, 2026
jakki-amd
pushed a commit
to jakki-amd/sglang
that referenced
this pull request
Sep 9, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reverts #28527 (
177c048c68).That change adds a second unconditional
process_weights_after_loading()pass in the diffusion FSDP loader. The hook is not idempotent for quantized weights, and the addeddevice_loading_contextalso breaks FSDP inference by attempting to restore CUDA-backed parameters to CPU storage.CI evidence:
multimodal-gen-test-2-gpu (2), wherefsdp-inferencefails indevice_loading_contextwith a CPU/CUDA storage mismatch.CI States
Latest PR Test (Base): ⏳ Run #29061437164
Latest PR Test (Extra): ❌ Run #29061437106