Fix: Disable torch.autocast in RotaryEmbedding of Gemma and LLaMa for MPS device #29439
Fix: Disable torch.autocast in RotaryEmbedding of Gemma and LLaMa for…
5a6a8384
Update src/transformers/models/gemma/modeling_gemma.py
3092a650
Update llama ang gemma rope use cpu in mps device
43484d9d
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub