Fedora 40 for aarch64 : / usr /lib64 /python3.12 /site-packages /onnxruntime /transformers

• __init__.py
• __pycache__
• affinity_helper.py
• benchmark.py
• benchmark_helper.py
• bert_perf_test.py
• bert_test_data.py
• compare_bert_results.py
• constants.py
• convert_generation.py
• convert_tf_models_to_pytorch.py
• convert_to_packing_mode.py
• float16.py
• fusion_attention.py
• fusion_attention_unet.py
• fusion_attention_vae.py
• fusion_bart_attention.py
• fusion_base.py
• fusion_bias_add.py
• fusion_biasgelu.py
• fusion_biassplitgelu.py
• fusion_embedlayer.py
• fusion_fastgelu.py
• fusion_gelu.py
• fusion_gelu_approximation.py
• fusion_gemmfastgelu.py
• fusion_gpt_attention.py
• fusion_gpt_attention_megatron.py
• fusion_gpt_attention_no_past.py
• fusion_group_norm.py
• fusion_layernorm.py
• fusion_nhwc_conv.py
• fusion_options.py
• fusion_qordered_attention.py
• fusion_qordered_gelu.py
• fusion_qordered_layernorm.py
• fusion_qordered_matmul.py
• fusion_reshape.py
• fusion_shape.py
• fusion_skiplayernorm.py
• fusion_transpose.py
• fusion_utils.py
• huggingface_models.py
• io_binding_helper.py
• machine_info.py
• models
• onnx_exporter.py
• onnx_model.py
• onnx_model_bart.py
• onnx_model_bert.py
• onnx_model_bert_keras.py
• onnx_model_bert_tf.py
• onnx_model_clip.py
• onnx_model_gpt2.py
• onnx_model_t5.py
• onnx_model_tnlr.py
• onnx_model_unet.py
• onnx_model_vae.py
• optimizer.py
• profiler.py
• quantize_helper.py
• shape_infer_helper.py
• shape_optimizer.py
• torch_onnx_export_helper.py

Generated by rpm2html 1.8.1

Fabrice Bellet, Sun Mar 9 18:21:05 2025