- 03 Dec, 2023 9 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
- 02 Dec, 2023 2 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
- 01 Dec, 2023 3 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
- 30 Nov, 2023 1 commit
-
-
Manupa Karunaratne authored
-
- 28 Nov, 2023 1 commit
-
-
music-dino authored
Add min and max reduction modes Implement duplicate index handling Add corresponding reference, onnx, and verify tests.
-
- 26 Nov, 2023 5 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
- 22 Nov, 2023 1 commit
-
-
Mirza Halilčević authored
Introduce dilations attribute to pooling operators reference implementation.
-
- 20 Nov, 2023 4 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
- 18 Nov, 2023 3 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
Umang Yadav authored
-
- 17 Nov, 2023 2 commits
-
-
Umang Yadav authored
-
Umang Yadav authored
-
- 15 Nov, 2023 1 commit
-
-
nives-vukovic authored
Since ONNX opset version 14, layout attribute has been introduced to LSTM operator which allows two predefined layouts for input and output shapes. Add corresponding reference, onnx, and verify tests.
-
- 08 Nov, 2023 2 commits
-
-
Zakor Gyula authored
The inaccuracy was caused by ONNX round requires nearest integer rounding for halway (0.5) cases. std::round rounds away from zero, thus giving wrong results with halfway cases. Replaced std::round with std::nearbyint which uses the correct rounding by default.
-
Brian Pickrell authored
-
- 07 Nov, 2023 1 commit
-
-
Zakor Gyula authored
-
- 30 Oct, 2023 1 commit
-
-
Umang Yadav authored
-
- 20 Oct, 2023 1 commit
-
-
Zakor Gyula authored
-
- 18 Oct, 2023 1 commit
-
-
Zakor Gyula authored
-
- 13 Oct, 2023 1 commit
-
-
turneram authored
-
- 12 Oct, 2023 1 commit
-
-
Manupa Karunaratne authored
Currently, we see MLIR partition candidates recieving non-standard shape due to not fusing in squeeze, flatten and unsqueeze ops. These ops could be canonicalized to reshape without introducing additional ops as long as MLIR backend is concerned.
-