transformers
Do not wrap the model in FSDP for expert-parallel token dispatch
#49383
Merged

Do not wrap the model in FSDP for expert-parallel token dispatch #49383

3outeille merged 1 commit into main from remove-fsdp-during-ep-inference
3outeille
3outeille Do not wrap the model in FSDP for expert-parallel token dispatch when…
793d09ee
3outeille 3outeille requested a review from vasqu vasqu 10 days ago
HuggingFaceDocBuilderDev
github-actions
vasqu
vasqu approved these changes on 2026-10-07
3outeille 3outeille requested a review from ArthurZucker ArthurZucker 10 days ago
3outeille
IlyasMoutawwakil
3outeille
ArthurZucker
ArthurZucker approved these changes on 2026-10-08
3outeille 3outeille merged cb33194a into main 10 days ago
3outeille 3outeille deleted the remove-fsdp-during-ep-inference branch 10 days ago
IlyasMoutawwakil
IlyasMoutawwakil

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone