fix(deepseek_v4): drop full-attention sharding for MoE-only strategy#1996
Open
adurham wants to merge 1 commit intoexo-explore:mainfrom
Open
fix(deepseek_v4): drop full-attention sharding for MoE-only strategy#1996adurham wants to merge 1 commit intoexo-explore:mainfrom
adurham wants to merge 1 commit intoexo-explore:mainfrom
Commits
Commits on Apr 27, 2026
- committed
Adam Durham