mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-24 19:43:35 +00:00
56ad68120e
Add support to use sequence as input ids in decoder inputs to Beam Search CUDA Op ### Description Currently Beam search Op is only supported for CPU EP, added support for CUDA EP. ### Motivation and Context - For Turing models inference was throwing segmentation fault due to copy failing in cuda memory, also beam search support was not present in cuda. |
||
|---|---|---|
| .. | ||
| aten_ops | ||
| attnlstm | ||
| bert | ||
| fp16 | ||
| math | ||
| quantization | ||
| tensor | ||
| transformers | ||
| utils | ||
| activations.cc | ||
| activations.h | ||
| cdist.cc | ||
| cdist.h | ||
| conv_transpose_with_dynamic_pads.cc | ||
| conv_transpose_with_dynamic_pads.h | ||
| cpu_contrib_kernels.cc | ||
| cpu_contrib_kernels.h | ||
| crop.cc | ||
| crop.h | ||
| crop_and_resize.cc | ||
| crop_and_resize.h | ||
| dynamicslice.cc | ||
| element_wise_ops.cc | ||
| element_wise_ops.h | ||
| expand_dims.cc | ||
| expand_dims.h | ||
| fused_activation.cc | ||
| fused_activation.h | ||
| fused_conv.cc | ||
| fused_gemm.cc | ||
| fused_matmul.cc | ||
| grid_sample.cc | ||
| image_scaler.cc | ||
| image_scaler.h | ||
| inverse.cc | ||
| layer_norm.cc | ||
| layer_norm.h | ||
| maxpool_with_mask.cc | ||
| maxpool_with_mask.h | ||
| mean_variance_normalization_exp.cc | ||
| murmur_hash3.cc | ||
| murmur_hash3.h | ||
| nchwc_ops.cc | ||
| nchwc_ops.h | ||
| sample.cc | ||
| sample.h | ||
| skip_layer_norm.cc | ||
| skip_layer_norm.h | ||
| tokenizer.cc | ||
| unique.cc | ||
| unique.h | ||
| word_conv_embedding.cc | ||
| word_conv_embedding.h | ||