Tipos de modelos limitados y especificaciones de software
Las especificaciones de software restringidas solo son compatibles en una instancia actualizada. No son compatibles con nuevas instalaciones, activos espaciales importados ni operaciones de parcheo.
Tipos de modelos limitados y especificaciones de software
La compatibilidad con las siguientes especificaciones de software es limitada:
| Infraestructura | Versiones | Tipo de modelo | Especificaciones predeterminadas del software | Plataformas compatibles |
|---|---|---|---|---|
| PyTorch | 1.10 | pytorch-onnx_1. 10pytorch-onnx_rt22.1 |
runtime-22.1-py3. 9pytorch-onnx_rt22.1-py3.9 pytorch-onnx_rt22.1-py3.9-edt |
x86 |
| PyTorch | 1.12 | pytorch-onnx_1. 12pytorch-onnx_rt22.2 |
runtime-22.2-py3.10 ( F)pytorch-onnx_rt22.2-py3.10 ( F)pytorch-onnx_rt22.2-py3.10-edt (F) | x86. PPC, s390x |
| PyTorch | 1.12 | pytorch-onnx_1. 12pytorch-onnx_rt22.2 |
pytorch-onnx_rt22.2-py3.10-dist(x86 ) (F) | x86 |
| PyTorch | 2.0 | pytorch-onnx_2.0 pytorch-onnx_rt23.1 |
runtime-23.1-py3.10 pytorch-onnx_rt23.1-py3.10 pytorch-onnx_rt23.1-py3.10-edt pytorch-onnx_rt23.1-py3.10-dist |
x86, s390x, PPC |
| Funciones de Python | N/D | N/D | runtime-22.1-py3.9 | x86 |
| Funciones de Python | N/D | N/D | runtime-22.2-py3.10 (F) runtime-23.1-py3.10 |
x86, PPC, s390x |
| Funciones de Python | N/D | N/D | runtime-23.1-py3.10-cuda | x86 |
| Scripts de Python | N/D | N/D | runtime-22.1-py3.9 | x86 |
| Scripts de Python | N/D | N/D | runtime-23.1-py3.10 | x86, s390x, PPC |
| Scripts de Python | N/D | N/D | runtime-22.2-py3.10 (F) | x86, PPC, s390x |
| Scripts R | N/D | N/D | default_r3.6 runtime-22.1-r3.6 runtime-22.2-r4.2 (F) |
x86 |
| Scripts R | N/D | N/D | runtime-23.1-r4.2 | x86. PPC |
| Aplicaciones R Shiny | N/D | N/D | shiny-r3.6 | x86. PPC |
| Aplicaciones R Shiny | N/D | N/D | rstudio_r4.2 | x86 |
| Aplicaciones R Shiny | N/D | N/D | rstudio-23.1-r4.2 | x86. PPC |
| Scikit-learn | 1.0 | scikit-learn_1.0 | runtime-22.1-py3.9 | x86 |
| Scikit-learn | 1.1 | scikit-learn_1.1 | runtime-22.2-py3.10 (F) runtime-23.1-py3.10 |
x86, PPC, s390x |
| Spark | 3.3 | mllib_3.3 | spark-mllib_3.3 | x86. PPC |
| Tensorflow | 2.7 | tensorflow_2. 7tensorflow_rt22.1 |
runtime-22.1-py3.9 tensorflow_rt22.1-py3.9 |
x86 |
| Tensorflow | 2.9 | tensorflow_2. 9tensorflow_rt22.2 |
runtime-22.2-py3.10 (F) tensorflow_rt22.2-py3.10 (F) |
x86, PPC, s390x |
| Tensorflow | 2.9 | tensorflow_2.94 .8.4tensorflow_rt22.2 |
tensorflow_rt22.2-py3.10-dist(x86 ) (F) tensorflow_rt22.2-py3.10-edt(x86) (F) |
x86, s390x, PPC |
| Tensorflow | 2.12 | tensorflow_2.12 tensorflow_rt23.1 |
runtime-23.1-py3.10 tensorflow_rt23.1-py3.10-dist tensorflow_rt23.1-py3.10-edt tensorflow_rt23.1-py3.10 |
x86, s390x, PPC |
| Tensorflow | 2.12 | tensorflow_2.12 tensorflow_rt23.1 |
runtime-23.1-py3.10-cuda | x86 |
| XGBoost | 1.5 | xgboost_1.5 o scikit-learn_1.0 (véanse las notas) | runtime-22.1-py3.9 | x86 |
| XGBoost | 1.6 | xgboost_1.6 o scikit-learn_1.1 | runtime-22.2-py3.10 (F) | x86, s390x, PPC |
| XGBoost | 1.6 | xgboost_1.6 o scikit-learn_1.1 (véanse las notas) | runtime-23.1-py3.10 | x86, s390x, PPC |
Importante:
En el caso de XGBoost, si el modelo se ha entrenado con el envoltorio de sklearn (XGBClassifier o XGBRegressor), utiliza el tipo scikit-learn_1.1 de modelo en Python3.10.
Tipos de modelos restringidos y especificaciones de software para modelos híbridos
| Infraestructura | Versiones | Tipo de modelo | Especificaciones del software predeterminado |
Especificaciones del software Pipeline | Plataforma compatible |
|---|---|---|---|---|---|
| Híbrido | 0.1 | wml-hybrid_0.1 | hybrid_0.1 | autoai-kb_rt22.1-py3.9 autoai-ts_rt22.1-py3.9 |
x86 |
| Híbrido | 0.1 | wml-hybrid_0.1 | hybrid_0.1 | autoai-kb_rt22.2-py3.10 (F) autoai-ts_rt22.2-py3.10 (F) autoai-kb_rt23.1-py3.10 autoai-ts_rt23.1-py3.10 autoai-tsad_rt23.1-py3.10 |
x86. PPC, s390x |