BioIR Package Installation
The following sections provide the steps to install the BioNeMo Inference Runtime (BioIR) package, along with the software and hardware requirements.
Requirements to Install the BioIR Wheel
The release wheel has the following software and hardware requirements:
- Operating system:
A Linux distribution that supports the latest NVIDIA drivers,
with glibc 2.34 or newer. Release wheels are tagged
manylinux_2_34, so pip reports no matching distribution on an older distribution such as Ubuntu 20.04 or RHEL 8. - CPU architecture: x86_64 (amd64) or aarch64 (arm64).
- GPU: An NVIDIA GPU listed in the support matrix.
- NVIDIA Driver: 580 or higher.
- Python: CPython 3.12, 3.13, or 3.14. Release wheels use
cp312-abi3. - Build tools: A C/C++ compiler and the active Python’s development headers. See Install Build Tools.
Use the commands in Collecting System Information to verify these requirements. If the installed NVIDIA driver is older than version 580, refer to the GPU Stack guide.
GPU Requirements
H200, H100, A100, L40S, GB200, and GB300 are release-qualified with measured speed, peak memory, and accuracy in the benchmarks.
BioIR also runs on other NVIDIA GPUs, including Ampere, Ada Lovelace, Hopper, and Blackwell. The support matrix distinguishes backend compatibility from release qualification and lists the optimized kernels for each architecture.
Driver Requirements
Use NVIDIA driver 580 or newer. BioIR is built against CUDA 13.2, but the wheel
does not need an NGC image or a CUDA Toolkit installed on the host. It requires
the driver-provided libcuda.so.1.
Drivers older than 580 are unsupported. The CUDA forward-compatibility shim caused hangs and crashes during inference testing on older drivers.
Check the installed GPU and driver with commands at Collecting System Information.
Choose an Installation Method
Choose one of the following installation methods based on your task:
- Release wheel (recommended): Install BioIR into a Python environment to call its models, optimized modules, and prediction pipeline from your code. This method is the simplest way to start using BioIR.
- Source build: Use the development container when changing BioIR or running its test suite. Follow the development workflow for Docker, NVIDIA Container Toolkit, compiler, and CUDA-header requirements.
Install the Release Wheel
BioIR is published on PyPI as bionemo-ir, with one wheel for each
supported CPU architecture. Each wheel supports CPython 3.12 through 3.14 using
the Python stable ABI. pip selects the wheel that matches the host.
Create a Python Environment
The release wheel supports CPython 3.12 through 3.14. A dedicated Python
environment is strongly recommended. It isolates BioIR and its dependencies
from the system Python and other projects. The examples below use Python 3.12;
replace 3.12 with 3.13 or 3.14 to use another supported version.
Choose one of the following methods to create and activate an environment:
uv (recommended)
conda
Python venv
Install uv. Its installer script needs curl or wget; on
Ubuntu, install curl with
sudo apt-get update && sudo apt-get install --yes curl. Open a new shell so
uv is on PATH, then run:
The --managed-python flag uses a uv-managed Python, which includes the
Python.h headers, instead of a system Python. The --seed flag installs
pip in the environment for the shared install commands below.
Keep the environment activated for the rest of this guide and for later work,
including the Quickstart. Confirm that it uses your chosen
supported Python version, then upgrade pip:
Install Build Tools
Every host needs a C compiler and the Python.h headers of the environment’s
Python interpreter. Triton, a PyTorch dependency, compiles a small C launcher
with them the first time BioIR runs a model.
pip also builds a dependency from source when PyPI has no wheel for the environment’s Python version and CPU architecture. The dependencies below need native build tools in the release’s tested dependency set. Other resolutions may differ; source builds add minutes to the install.
pip builds ihm from source on every host. Its C extension is optional, so
ihm installs without a compiler.
uv-managed and conda Pythons include Python.h. A Python from the
distribution’s package manager needs its matching development package as well.
Check the environment’s interpreter:
Install the compilers, then the development package only when the check
prints False. The development package examples use Python 3.12; substitute
your environment’s Python minor version when it differs:
Ubuntu
RHEL family
To list the dependencies that build from source on this host, run the following check before installing BioIR. It compiles nothing:
The result means:
- Ends with
Would install: Every dependency exceptihminstalls from a wheel. ResolutionImpossible: The lines underThe conflict is caused by:name a dependency that builds from source, such askalign-python.No matching distribution found for bionemo-ir: The Python version or glibc does not match the release wheel. Check the requirements.No matching distribution found foranother package: That dependency builds from source.
pip names only the first dependency that builds from source.
Install the Package
The external materials notice applies to the dependencies downloaded separately by pip.
Install BioIR into the active environment:
pip resolves PyTorch, the CUDA libraries, and the remaining dependencies from
the same index. The wheel carries the GPU kernels precompiled, so neither
installing nor running BioIR needs nvcc or the CUDA Toolkit.
If pip fails to build a dependency, or the first prediction fails to compile Triton’s launcher, match the error to the build tools it needs:
fatal error: Python.h: No such file or directory,Could NOT find Python (missing: ... Development.Module), orImported target "pybind11::module" includes non-existent path: Install the-devor-develpackage for your Python version, for examplepython3.12-devorpython3.12-devel. During a prediction, the first error appears above aCalledProcessErrornaming Triton’sdriver.c.Failed to find C compiler,No such file or directory: 'gcc'or'cc',no acceptable C compiler found, or a CMake error namingCMAKE_C_COMPILERorCMAKE_CXX_COMPILER: Install the compilers.
Verify the install:
On aarch64, python -m pip check can report
nvidia-cusparselt-cu13 0.8.1 is not supported on this platform because the
upstream cuSPARSELt wheel declares an incorrect internal platform tag. This
warning does not prevent installation or package imports. No post-install
repair is required.
Next Steps
- Run your first Boltz-2 prediction in the Quickstart.
- Use the
build_processorAPI to run a supported structure-prediction pipeline. - Review the model and GPU support matrix.
- Follow the development workflow to build, test, or contribute to BioIR.