mirror of
https://github.com/nod-ai/SHARK-Studio.git
synced 2026-01-14 16:28:01 -05:00
* Fix sharktank generation and add batch_size pytest option for torch. * Disable torch dynamo until py3.11 supported * Compile torchmodel without dynamo if torch.compile fails * Use release versions of TF/Keras for importer. * Pin torchvision and remove debug prints. * Remove duplicates from torch model list. * Update generate_sharktank.py * xfail a few models that fail sharktank generation/ numerics