You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* Upgrade use CUDA 13
Signed-off-by: M Q <mingmelvinq@nvidia.com>
* More update to the CI workflows for CUDA 13
Signed-off-by: M Q <mingmelvinq@nvidia.com>
* Addressed AI Agent comments on GenAI code
Signed-off-by: M Q <mingmelvinq@nvidia.com>
* Nit pick on formatting
Signed-off-by: M Q <mingmelvinq@nvidia.com>
* Nits in the README
Signed-off-by: M Q <mingmelvinq@nvidia.com>
---------
Signed-off-by: M Q <mingmelvinq@nvidia.com>
- This SDK depends on [NVIDIA Holoscan SDK](https://pypi.org/project/holoscan/) for its core implementation as well as its CLI, hence inherits its prerequisites, e.g. Ubuntu 22.04 with glibc 2.35 on X86-64 and NVIDIA dGPU drivers version 535 or above. Important to note that `holoscan` and `holoscan-cli` up to v4.2 are compatible.
42
-
- Key runtime dependencies also include [nvidia-nvimgcodec](https://pypi.org/project/nvidia-nvimgcodec-cu12/) and its own dependencies for GPU accecelerated DICOM image decoding.
43
-
-[CUDA 12.2](https://developer.nvidia.com/cuda-12-2-0-download-archive) or above is required along with a supported NVIDIA GPU with at least 8GB of video RAM.
44
-
- If inference is not used in an example application and a GPU is not installed, at least [CUDA 12 runtime](https://pypi.org/project/nvidia-cuda-runtime-cu12/) is required, as this is one of the requirements of Holoscan SDK. In addition, the `LIB_LIBRARY_PATH` must be set to include the installed shared library, e.g. in a Python 3.10 env, ```export LD_LIBRARY_PATH=`pwd`/.venv/lib/python3.10/site-packages/nvidia/cuda_runtime/lib:$LD_LIBRARY_PATH```
41
+
- This SDK depends on [NVIDIA Holoscan SDK (CUDA 13)](https://pypi.org/project/holoscan-cu13/) for its core implementation as well as its CLI, hence inherits its prerequisites, e.g. Ubuntu 22.04 with glibc 2.35+ (see output of ldd --version) and CUDA Runtime 13.0 or above. It is important to note that `holoscan-cu13` and `holoscan-cli` up to version 4.2 are compatible.
42
+
- Key runtime dependencies also include [nvidia-nvimgcodec](https://pypi.org/project/nvidia-nvimgcodec-cu13/) and its own dependencies for GPU-accelerated DICOM image decoding.
43
+
-[CUDA 13.0](https://developer.nvidia.com/cuda-downloads) or above is required along with a supported NVIDIA GPU with at least 8GB of video RAM.
44
+
- If inference is not used in an example application and a GPU is not installed, at least [CUDA 13 runtime](https://pypi.org/project/nvidia-cuda-runtime/) is required, as this is one of the requirements of Holoscan SDK. In addition, the `LD_LIBRARY_PATH` must be set to include the installed shared library, e.g. in a Python 3.10 env, ```export LD_LIBRARY_PATH=`pwd`/.venv/lib/python3.10/site-packages/nvidia/cu13/lib:$LD_LIBRARY_PATH```
0 commit comments