transformers
fix(granitemoe*): Only create block_sparse_moe if num_local_experts > 0
#42036
Merged

fix(granitemoe*): Only create block_sparse_moe if num_local_experts > 0 #42036

gabe-l-hart
gabe-l-hart
gabe-l-hart
gabe-l-hart
gabe-l-hart
gabe-l-hart commented on 2025-11-05
gabe-l-hart
gabe-l-hart commented on 2025-11-05
gabe-l-hart gabe-l-hart force pushed from e1e87db8 to be876f8a 292 days ago
gabe-l-hart
gabe-l-hart gabe-l-hart force pushed from be876f8a to 1257cedc 292 days ago
gabe-l-hart fix(granitemoehybid): Only set self.block_sparse_moe if num_local_exp…
7a6b4ebe
gabe-l-hart fix(granitemoehybrid): Regenerate modeling_granitemoehybrid.py
f0cebbb8
gabe-l-hart gabe-l-hart force pushed from 1257cedc to f0cebbb8 292 days ago
gabe-l-hart
gabe-l-hart
gabe-l-hart commented on 2025-11-05
Rocketknight1
gabe-l-hart
gabe-l-hart style: Fix import order
c10b1cc7
Rocketknight1
gabe-l-hart Merge branch 'main' into GraniteMoeAsDenseFix
b8a50cfb
gabe-l-hart Merge branch 'main' into GraniteMoeAsDenseFix
b5f118d8
gabe-l-hart
Rocketknight1 make fix-copies
340b546b
github-actions
Rocketknight1
Rocketknight1 approved these changes on 2025-11-20
Rocketknight1 Merge branch 'main' into GraniteMoeAsDenseFix
f469bbf7
Rocketknight1 Rocketknight1 enabled auto-merge (squash) 277 days ago
Rocketknight1 Rocketknight1 merged a1afecae into main 277 days ago
HuggingFaceDocBuilderDev
gabe-l-hart gabe-l-hart deleted the GraniteMoeAsDenseFix branch 266 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone