Sai Jayanthi

icon indicating an email [email protected]

icon company Intel icon location Hillsboro, Oregon, USA icon location Power and Performance Architect for AI workloads at Intel.

Results 3 issues of Sai Jayanthi

Are FastRCNN models from TorchVision supported in TRTorch?

9 comment

## ❓ Question Tried FastRCNN and MaskRCNN models from TorchVision. The model fails to compile with error "RuntimeError: tuple appears in op that does not forward tuples, unsupported kind: aten::append"...

feature request
question
component: lowering
component: partitioning

Adding tests for torch-ort-infer

This PR adds tests for openvino provider options API along with basic unit tests.

CLA Signed

[torch-ort-infer] Aten fallback doesn't work

6 comment

Aten op doesn't fallback to native pytorch runtime as expected. **Versions:** Torch - 1.12.0 OnnxRuntime - 1.12.0 Torch-ort-infer - 1.12.0 **Reproduction steps:** ``` import torch from torch_ort import ORTInferenceModule def...