Patch DeepSeek V3 config to add missing qk_head_dim attribute if needed#723
Open
Edwardf0t1 wants to merge 1 commit intomainfrom
Open
Patch DeepSeek V3 config to add missing qk_head_dim attribute if needed#723Edwardf0t1 wants to merge 1 commit intomainfrom
Edwardf0t1 wants to merge 1 commit intomainfrom