Get Started

BioIR Package Installation

View as Markdown

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.
  • CPU architecture: x86_64 (amd64) or aarch64 (arm64).
  • GPU: An NVIDIA GPU listed in the support matrix.
  • NVIDIA Driver: 580 or higher.
  • Python: Python 3.12. Release wheels are tagged cp312.
  • aarch64 build tools: A C/C++ compiler and Python 3.12 development headers. Some transitive dependencies build from source on aarch64.

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 CUDA Toolkit does not need to be installed on the host. BioIR 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

The latest GitHub release contains one wheel for each supported CPU architecture. Install the gh CLI and log in with read access to NVIDIA-BioNeMo/BioNeMo-Inference-Runtime.

Install aarch64 Build Prerequisites

On Ubuntu 24.04 aarch64, install the compiler toolchain and Python headers used to build transitive dependencies:

$sudo apt-get update
$sudo apt-get install --yes build-essential python3.12-dev

The python3.12-dev package provides Python.h.

Create a Python Environment

The release wheel requires Python 3.12 (cp312). A dedicated Python environment is strongly recommended. It isolates BioIR and its dependencies from the system Python and other projects.

Choose one of the following methods to create and activate an environment:

Install uv, then run:

$uv venv --python 3.12 --seed .venv
$source .venv/bin/activate

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 Python 3.12, then upgrade pip:

$python --version
$python -m pip install --upgrade pip

Download the Wheel

Download the wheel that matches your CPU architecture. uname -m reports x86_64 or aarch64. With no release tag, gh selects the latest release.

Run this command on an x86_64 host:

$gh release download \
>  --repo NVIDIA-BioNeMo/BioNeMo-Inference-Runtime \
>  --pattern "*_amd64_bionemo_ir-*.whl" --pattern SHA256SUMS

Run this command on an aarch64 host:

$gh release download \
>  --repo NVIDIA-BioNeMo/BioNeMo-Inference-Runtime \
>  --pattern "*_arm64_bionemo_ir-*.whl" --pattern SHA256SUMS

Verify the Checksum

Verify the downloaded assets against SHA256SUMS:

$sha256sum --check --ignore-missing SHA256SUMS

Restore the Wheel Filename

The downloaded asset name includes a bundle prefix, and GitHub replaces the wheel version’s + with .. Restore a pip-valid name after the checksum check:

$for asset in *_bionemo_ir-*.whl; do
$  wheel=bionemo_ir-${asset#*_bionemo_ir-}
$  wheel=$(printf '%s\n' "$wheel" | sed -E 's/\.cu([0-9]+)([.-])/+cu\1\2/')
$  mv "$asset" "$wheel"
$done

Install the Wheel

Install the restored wheel into the active environment:

$python -m pip install ./bionemo_ir-*.whl

Next Steps