onnxruntime
onnxruntime copied to clipboard
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
### Describe the feature request There were some new APIs introduced earlier in the year to streamline the process of compiling ORT models, i.e., https://onnxruntime.ai/docs/api/c/struct_ort_compile_api.html. These APIs can accept the...
### Describe the issue pip install onnxruntime ERROR: Could not find a version that satisfies the requirement onnxruntime (from versions: none) ERROR: No matching distribution found for onnxruntime ### To...
### Description - Input pb files were read in incorrect order. - Cause: Python `sorted` was used to acquire sorted input files in order. However, the input files would be...
- add the WebGPU FormatTransform kernel, headers, and WGSL template, supporting Plain nChw4c/ABcd16a4b conversions - register the FormatTransform schema in the internal NHWC domain with padding-aware shape inference - hook...
Bumps [clang-format](https://github.com/ssciwr/clang-format-wheel) from 20.1.8 to 21.1.7. Commits 771aa87 v21.1.7 5a145d8 Merge pull request #149 from ssciwr/ci 3747556 Update deprecated macos-13 intel mac runner to use macos-15-intel, bump actions b43cdff v21.1.6...
Bumps [ruff](https://github.com/astral-sh/ruff) from 0.12.12 to 0.14.8. Release notes Sourced from ruff's releases. 0.14.8 Release Notes Released on 2025-12-04. Preview features [flake8-bugbear] Catch yield expressions within other statements (B901) (#21200) [flake8-use-pathlib]...
### Describe the issue As the title says, when Conv node is used on WebGPU with strides>1 and auto_pad e.g. "SAME_UPPER", it produces values that are very much off the...