ONNX Community Day 2024
9:00am: Introduction (15 mins) | |
Event kick-off and Welcome keynote | Ramakrishnan Sivakumar and |
ONNX Steering committee progress update | Steering committee |
Community Presentation | |
P1: Neural Compressor Overview | Mengni Wang |
P2: Towards an embedded profile for ONNX | Eric Jenn |
P3: Using Olive with ONNX to accelerate generative AI on AMD | Sonbol Yazdanbakhsh |
P4: Streamlining Model Design and Optimization with Nsight DL |
|
P5: Unifying ONNX with the Array API - export to ONNX with no |
|
P6: Transforming ONNX graphs with ONNX IR and the Rewriter |
|
P7: How to Win Friends and Influence Hardware |
|
P8: Accelerating ONNX graphs using OpenMP in ONNX-MLIR |
|
P9: ONNXRuntime Training on Web |
|
P10: Background Removal in the Browser |
|
P11: Inference Optimization with ONNX Runtime |
|
P12: Expressing very large feature engineering pipelines in ONNX |
|
P13: Model Openness Framework |
|
SIG & WG Updates |
|
SIG update 1: Architecture & Infra |
|
SIG update 2: Compilers |
|
SIG update 3: Converters |
|
SIG update 4: Models & Tutorials |
|
SIG update 5: Optimizations |
|
SIG update 6: Operators |
|
WG update: Multi-Device WG |
|
Panel Discussion |
|
Conclusion |
|
Closing thoughts |
|
|
|