search

ROCm / pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration
http://pytorch.org
Other
219 stars 50 forks source link

[ROCm] Integrate hipblasLT AMAX_D pointer #1406

Closed alugorey closed 2 months ago

alugorey commented 2 months ago

Reverts the AMAX workaround now that hipblasLT supports AMAX. hipblasLT does not like getting nullptr for scale D so we create a dummy scalar tensor with the value of 1.0 to pass in the event we are about to pass a nullptr