search

ROCm / pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration
http://pytorch.org
Other
219 stars 51 forks source link

Added cublasGemmAlgo_t -> hipblasGemmAlgo_t #1416

Closed rraminen closed 4 months ago

rraminen commented 4 months ago

This PR is to add cublasGemmAlgo_t -> hipblasGemmAlgo_t to cuda_to_hip_mappings.py. It is required for DeepSpeed transformer extension build on ROCm.