mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-14 20:48:00 +00:00
e726151b5c
### Description The PR implements FloatE4M3FN, FloatE5M2, FloatE4MEFNUZ, FloatE5M2FNUZ as described in PR https://github.com/onnx/onnx/pull/4805. It uses CUDA API to cast float/half to float8 if CUDA>=11.8, a custom implementation if CUDA<11.8. * It implements, Cast, QuantizeLinear, DequantizeLinear for all types on CPU, only for types FloatE4M3FN, FloatE5M2 on CUDA. * It extends the supported types for control flow operator, Shape, Reshape, Identity, If, Loop, Scan, Reshape * It implements Equal(19). * Cast, QuantizeLinear, DequantizeLinear operators now support a parameter `saturate` only valid for float 8 types. It is true by default. In that case, any value out of range is converted into the maximum float 8 value. If false, it is infinite. * QuantizeLinear, DequantizeLinear now supports multiple scales on CUDA (and ROCm by extension), scale = 1D tensor with one scale per channel ### Motivation and Context Supports latest onnx version. Fixes [AB#15395](https://aiinfra.visualstudio.com/6a833879-cd9b-44a4-a9de-adc2d818f13c/_workitems/edit/15395) --------- Co-authored-by: Xavier Dupre <xadupre@microsoft.com@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net> Co-authored-by: Randy Shuai <rashuai@microsoft.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Scott McKay <Scott.McKay@microsoft.com> |
||
|---|---|---|
| .. | ||
| android | ||
| mobile_helpers | ||
| ort_format_model | ||
| qdq_helpers | ||
| test | ||
| __init__.py | ||
| __init__append.py | ||
| check_onnx_model_mobile_usability.py | ||
| convert_onnx_models_to_ort.py | ||
| file_utils.py | ||
| get_azcopy.py | ||
| logger.py | ||
| make_dynamic_shape_fixed.py | ||
| onnx_model_utils.py | ||
| optimize_onnx_model.py | ||
| platform_helpers.py | ||
| pytorch_export_helpers.py | ||
| reduced_build_config_parser.py | ||
| run.py | ||
| update_onnx_opset.py | ||