stevxiao a077da895b avfilter/dnn_backend_torch: add CUDA/ROCm device support ...

Add support for CUDA and ROCm (AMD GPU) devices in the LibTorch DNN
backend.

This works for both NVIDIA CUDA and AMD ROCm, as PyTorch exposes ROCm
through the CUDA-compatible API.

Usage:

./ffmpeg -i input.mp4 -vf scale=224:224,format=rgb24,dnn_processing=dnn_backend=torch:model=sr_model_torch.pt:device=cuda output.mp4

Reviewed-by: Guo Yejun <yejun.guo@intel.com>
Signed-off-by: younengxiao <steven.xiao@amd.com>

2026-03-21 16:25:40 +08:00

..

dnn_backend_common.c

…

dnn_backend_common.h

…

dnn_backend_openvino.c

…

dnn_backend_tf.c

avfilter/dnn_backend_tf: fix ctx async field access

2026-03-20 02:22:06 +00:00

dnn_backend_torch.cpp

avfilter/dnn_backend_torch: add CUDA/ROCm device support

2026-03-21 16:25:40 +08:00

dnn_interface.c

avfilter/dnn: fix missing set default value to options

2026-03-06 21:41:11 +08:00

dnn_io_proc.c

…

dnn_io_proc.h

…

Makefile

…

queue.c

…

queue.h

…

safe_queue.c

…

safe_queue.h

…