pengwa 1a0ba3f69f Fix softmax export (#20057) ... ### Description Why we need to define softmax export logic here? For the usage `nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32)` in the model, 76a33a1092/src/transformers/models/mistral/modeling_mistral.py (L302) If dtype is specified, the input tensor is casted to dtype before the operation is performed. This is useful for preventing data type overflows. While existing ONNX exporter do the cast after the operation, which is not correct. (cf06189a2d/torch/onnx/symbolic_opset13.py (L27)). This override can be a workaround before PyTorch fix the issues in coming releases. (TODO: pengwa - add PyTorch versions when the issue is fixed). @thiagocrepaldi We may need a fix in PyTorch repo as well. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->		2024-03-26 13:09:20 +08:00
..
orttraining	Fix softmax export (#20057)	2024-03-26 13:09:20 +08:00
tools	Bump ruff to 0.3.2 and black to 24 (#19878)	2024-03-13 10:00:32 -07:00