transformers
8fce0a18 - Fix `FP8Expert` for DeepSeek R1 (#43616)

Commit
29 days ago
Fix `FP8Expert` for DeepSeek R1 (#43616) * use moe_intermediate_size for ds Signed-off-by: yiliu30 <yi4.liu@intel.com> * format Signed-off-by: yiliu30 <yi4.liu@intel.com> --------- Signed-off-by: yiliu30 <yi4.liu@intel.com> Co-authored-by: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>
Author
Parents
Loading