transformers
7f6cc4b3 - Add MoE to Gemma4 TP plan (#45219)

Commit
99 days ago
Add MoE to Gemma4 TP plan (#45219) reduce memory for gemma4 moe model in tp Signed-off-by: Wang, Yi <yi.a.wang@intel.com> Co-authored-by: Cyril Vallez <cyril.vallez@huggingface.co>
Author
Parents
Loading