Skip to content

fix: FSDP pre-shard combined projections on dim 1 for Qwen2.5-7B supp…

35347d6
Select commit
Loading
Failed to load commit list.
Open

fix: cherry-pick combined projection fixes (#1324, #1357) into r0.2.1 #1388

fix: FSDP pre-shard combined projections on dim 1 for Qwen2.5-7B supp…
35347d6
Select commit
Loading
Failed to load commit list.