The Holoscan SDK: building high-performance AI streaming applications
Project description
Holoscan SDK
The Holoscan SDK Python Wheel is part of NVIDIA Holoscan, the AI sensor processing platform that combines hardware systems for low-latency sensor and network connectivity, optimized libraries for data processing and AI, and core microservices to run streaming, imaging, and other applications, from embedded to edge to cloud. It can be used to build streaming AI pipelines for a variety of domains, including Medical Devices, High Performance Computing at the Edge, Industrial Inspection and more.
Getting Started
Visit the Holoscan User Guide to get started with the Holoscan SDK.
Prerequisites
- Prerequisites for each supported platform are documented in the user guide. Note that the python wheels have a lot of optional dependencies which you may install manually based on your needs (see compatibility matrix at the bottom).
- The Holoscan SDK python wheels are only formally tested on Ubuntu 22.04. They are, however, expected to work on any Linux distribution with glibc 2.35 or above (see output of
ldd --version
) and CUDA Runtime 12.2 or above. - Python: 3.8 to 3.11
Troubleshooting
Version 0.6.0 gets installed instead of the latest version
The latest version of the wheels were built and tested on Ubuntu 22.04 with glibc 2.35. You'll need to switch to a Linux distribution with a more recent version of glibc to use the Holoscan SDK python wheels 1.0 or above (check your version with ldd --version
), or use the Holoscan SDK NGC container instead.
ERROR: Could not find a version that satisfies the requirement holoscan==<version> ERROR: No matching distribution found for holoscan==<version>
Same as above, OR incompatible python version.
libc.so.6: version 'GLIBC_2.32 not found libstdc++.so.6: version `GLIBCXX_3.4.29` not found
Same as above.
ImportError: libcudart.so.12: cannot open shared object file: No such file or directory
CUDA runtime is missing from your system (required even for CPU only pipelines).
- x86_64: Follow the official installation steps.
- Note: while Holoscan does not use the CUDA Python API, you could install the CUDA runtime python wheel if you prefer to use
pip
instead of installing it system-wide:python3 -m pip install nvidia-cuda-runtime-cu12
. Before calling an Holoscan application, ensure to update yourLD_LIBRARY_PATH
environment variable to include the path to these CUDA libs, for example:export CUDA_WHL_LIB_DIR=$(python3 -c 'import nvidia.cuda_runtime; print(nvidia.cuda_runtime.__path__[0])')/lib export LD_LIBRARY_PATH="$CUDA_WHL_LIB_DIR:$LD_LIBRARY_PATH"
- Note: while Holoscan does not use the CUDA Python API, you could install the CUDA runtime python wheel if you prefer to use
- IGX Orin: Ensure the compute stack is installed.
- Jetson: Re-install JetPack 6.0.
Error: libnvinfer.so.8: cannot open shared object file: No such file or directory ... Error: libnvonnxparser.so.8: cannot open shared object file: No such file or directory
TensorRT is missing from your system (note that it is only needed by the holoscan.operators.InferenceOp
operator.).
- x86_64: Follow the official installation steps.
- Note: you can also install the TensorRT libraries python wheel if you prefer to use
pip
instead of installing it system-wide:python3 -m pip install tensorrt-libs~=8.6.1 --index-url https://pypi.nvidia.com
. Before calling an Holoscan application, ensure to update yourLD_LIBRARY_PATH
environment variable to include the path to these TensorRT libs, for example:export TRT_WHL_LIB_DIR=$(python3 -c 'import tensorrt_libs; print(tensorrt_libs.__path__[0])') export CUDNN_WHL_LIB_DIR=$(python3 -c 'import nvidia.cudnn; print(nvidia.cudnn.__path__[0])')/lib export CUBLAS_WHL_LIB_DIR=$(python3 -c 'import nvidia.cublas; print(nvidia.cublas.__path__[0])')/lib export LD_LIBRARY_PATH="$TRT_WHL_LIB_DIR:$CUDNN_WHL_LIB_DIR:$CUBLAS_WHL_LIB_DIR:$LD_LIBRARY_PATH"
- Note: you can also install the TensorRT libraries python wheel if you prefer to use
- IGX Orin: Ensure the compute stack is installed.
- Jetson: Re-install JetPack 6.0.
from pip._internal.models.scheme import SCHEME_KEYS ModuleNotFoundError: No module named 'pip' ... ImportError: libholoscan_core.so.2: cannot open shared object file: No such file or directory
Your version of pip
is either too old (< 20.2) or you are trying to install holoscan
with system pip
which cannot be found to resolve the Holoscan library symlinks.
To resolve, either:
- install
holoscan
in a virtual environment, or - uninstall
holoscan
, upgrade pip on your system withpython3 -m pip install --upgrade pip
, and reinstallholoscan
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distributions
File details
Details for the file holoscan-2.4.0-cp311-cp311-manylinux_2_35_x86_64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp311-cp311-manylinux_2_35_x86_64.whl
- Upload date:
- Size: 34.7 MB
- Tags: CPython 3.11, manylinux: glibc 2.35+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 66ab97b2f4536f3ede125669c3c9231a4ecc9853e784b908aff0e727041beeb6 |
|
MD5 | a35827be4d8411bc5b9e95ea766da7d9 |
|
BLAKE2b-256 | 23b0e2c852cb64e933723568669a25b390720ae0ecaa6e5a7353bdaf208bcc46 |
File details
Details for the file holoscan-2.4.0-cp311-cp311-manylinux_2_35_aarch64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp311-cp311-manylinux_2_35_aarch64.whl
- Upload date:
- Size: 33.0 MB
- Tags: CPython 3.11, manylinux: glibc 2.35+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c5306cc97a0760db886983c24dc89400f8bd0266b8b42b02f5d4af3b5ade0e39 |
|
MD5 | baa238bcbd35878eacfb3e06a842e8be |
|
BLAKE2b-256 | 62f267c16e05a49eca70a8753f0a51e0e301d4f34723dc2bb1ffc11388069bce |
File details
Details for the file holoscan-2.4.0-cp310-cp310-manylinux_2_35_x86_64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp310-cp310-manylinux_2_35_x86_64.whl
- Upload date:
- Size: 34.6 MB
- Tags: CPython 3.10, manylinux: glibc 2.35+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5da45a4a1aaa2548fe2373643244c5c14163741c24edda564b2bf16036bec7ae |
|
MD5 | 639d2217ffada8b3454ee72d586ccaa6 |
|
BLAKE2b-256 | 5f35eeacac84bb5c6970fd0d373310c657431292cfc4d61f0ccd26b2d51d59b9 |
File details
Details for the file holoscan-2.4.0-cp310-cp310-manylinux_2_35_aarch64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp310-cp310-manylinux_2_35_aarch64.whl
- Upload date:
- Size: 33.0 MB
- Tags: CPython 3.10, manylinux: glibc 2.35+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5af94b8b12c974bf4b1887efbf03d7fdac17302d8871ba866b63f0ab00e250c4 |
|
MD5 | 5a9a62b5f6a8f8982801163eed9cd6cd |
|
BLAKE2b-256 | 686e7fcd41e3ffcc2f059b631b68970acb6dadd2c772643e9df6fdd1a48cea28 |
File details
Details for the file holoscan-2.4.0-cp39-cp39-manylinux_2_35_x86_64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp39-cp39-manylinux_2_35_x86_64.whl
- Upload date:
- Size: 34.6 MB
- Tags: CPython 3.9, manylinux: glibc 2.35+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6ae30665a4c3403689e86f7632fafd20d064890ad9d454592466084dc7eef493 |
|
MD5 | 3e48e45b959ea6c3ee11c73801f2a4f1 |
|
BLAKE2b-256 | 8f096229a4d3a6aacd74b81a01e724cfde20ee54fe3149cb455ffc1ade5c8f53 |
File details
Details for the file holoscan-2.4.0-cp39-cp39-manylinux_2_35_aarch64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp39-cp39-manylinux_2_35_aarch64.whl
- Upload date:
- Size: 33.0 MB
- Tags: CPython 3.9, manylinux: glibc 2.35+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | ffae94a360c818f1e3ca6239d43861803900f162b24f291f9ab2aeac041d8613 |
|
MD5 | 0d2ea89ac4a82357572d9cf090463d26 |
|
BLAKE2b-256 | 78056fd04c31d93d00405935f0ffa03afa892b7aac45cc5866ab44a5b6b585a2 |
File details
Details for the file holoscan-2.4.0-cp38-cp38-manylinux_2_35_x86_64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp38-cp38-manylinux_2_35_x86_64.whl
- Upload date:
- Size: 34.6 MB
- Tags: CPython 3.8, manylinux: glibc 2.35+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 04b1a68b7765845e7e6928c7f94b40056da4fd38614fe3ed2c674313f2060e99 |
|
MD5 | 5a14b2fe4f0d5b4590c16526cc2bfb7a |
|
BLAKE2b-256 | 491c1f49431f56d12ba13b05514d55ab8030a203e443f9e8ed0c2957f367d103 |
File details
Details for the file holoscan-2.4.0-cp38-cp38-manylinux_2_35_aarch64.whl
.
File metadata
- Download URL: holoscan-2.4.0-cp38-cp38-manylinux_2_35_aarch64.whl
- Upload date:
- Size: 33.0 MB
- Tags: CPython 3.8, manylinux: glibc 2.35+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4e23fb9bb74ee0214eeb8bc94591b79f3e53065bcc2835a694dd99cdb2c4c737 |
|
MD5 | 4dbb8e398b534a504d8150ffa2234924 |
|
BLAKE2b-256 | 268bd79aa3e21bbe6d4b1d140836d752a875feba49642dbb011b19eae0ba0c5a |