Pin optimum export stack to reproducible versions
Browse filesThe previous fix relied on pip happening to resolve a compatible
optimum/optimum-onnx/transformers combination on Python 3.13. With
those left unpinned, a resolver drift (or a future 3.14 base-image
bump) could reintroduce the NormalizedConfig 'allow_new' TypeError
that broke every conversion.
Pin the three packages that determine exporter behavior to the
versions verified working (optimum 2.1.0, optimum-onnx 0.1.0,
transformers 4.57.6), and pin onnx-ir 0.2.1 since onnxruntime imports
it lazily without declaring it. The onnx/onnxruntime/onnxconverter-common
floors are kept as-is; they encode real minimums (quantizer classes,
float16 API stability).
- requirements.txt +4 -2
requirements.txt
CHANGED
|
@@ -3,8 +3,10 @@ streamlit==1.50.0
|
|
| 3 |
PyYAML==6.0.2
|
| 4 |
torch==2.5.1; python_version < "3.13"
|
| 5 |
torch>=2.9.0; python_version >= "3.13"
|
| 6 |
-
optimum[onnx]
|
|
|
|
|
|
|
| 7 |
onnx>=1.22
|
| 8 |
onnxruntime>=1.27
|
| 9 |
-
onnx-ir
|
| 10 |
onnxconverter-common>=1.16,<1.17
|
|
|
|
| 3 |
PyYAML==6.0.2
|
| 4 |
torch==2.5.1; python_version < "3.13"
|
| 5 |
torch>=2.9.0; python_version >= "3.13"
|
| 6 |
+
optimum[onnx]==2.1.0
|
| 7 |
+
optimum-onnx==0.1.0
|
| 8 |
+
transformers==4.57.6
|
| 9 |
onnx>=1.22
|
| 10 |
onnxruntime>=1.27
|
| 11 |
+
onnx-ir==0.2.1
|
| 12 |
onnxconverter-common>=1.16,<1.17
|