Link to this sectionAxelera AI Export and Deployment#

Ultralytics partners with Axelera AI to enable high-performance, energy-efficient inference on Edge AI devices. Export and deploy Ultralytics YOLO models directly to the Metis® AIPU using the Voyager SDK.

Axelera AI provides dedicated hardware acceleration for computer vision at the edge, using a proprietary dataflow architecture and in-memory computing to deliver up to 856 TOPS with low power consumption.

Link to this sectionSelecting the Right Hardware#

Axelera AI offers various form factors to suit different deployment constraints. The chart below helps identify the optimal hardware for your Ultralytics YOLO deployment.

graph TD
    A[Start: Select Deployment Target] --> B{Device Type?}
    B -->|Edge Server / Workstation| C{Throughput Needs?}
    B -->|Embedded / Robotics| D{Space Constraints?}
    B -->|Standalone / R&D| E[Dev Kits & Systems]

    C -->|Max Density <br> 30+ Streams| F[**Metis PCIe x4**<br>856 TOPS]
    C -->|Standard PC <br> Low Profile| G[**Metis PCIe x1**<br>214 TOPS]

    D -->|Drones & Handhelds| H[**Metis M.2**<br>2280 M-Key]
    D -->|High Performance Embedded| I[**Metis M.2 MAX**<br>Extended Thermal]

    E -->|ARM-based All-in-One| J[**Metis Compute Board**<br>RK3588 + AIPU]
    E -->|Prototyping| K[**Arduino Portenta x8**<br>Integration Kit]

    click F "https://store.axelera.ai/"
    click G "https://store.axelera.ai/"
    click H "https://store.axelera.ai/"
    click J "https://store.axelera.ai/"

Link to this sectionHardware Portfolio#

The Axelera hardware lineup is optimized to run Ultralytics YOLO26 and legacy versions with high FPS-per-watt efficiency.

Link to this sectionAccelerator Cards#

These cards enable AI acceleration in existing host devices, facilitating brownfield deployments.

Link to this sectionIntegrated Systems#

For turnkey solutions, Axelera partners with manufacturers to provide systems pre-validated for the Metis AIPU.

• Metis Compute Board: A standalone edge device pairing the Metis AIPU with a Rockchip RK3588 ARM CPU.
• Workstations: Enterprise towers from Dell (Precision 3460XE) and Lenovo (ThinkStation P360 Ultra).
• Industrial PCs: Ruggedized systems from Advantech and Aetina designed for manufacturing automation.

Link to this sectionSupported Tasks#

The following tasks are supported across YOLOv8, YOLO11, and YOLO26 models.

Link to this sectionInstallation#

Link to this sectionUltralytics Installation#

pip install ultralytics

For detailed instructions, see our Ultralytics Installation guide. If you encounter difficulties, consult our Common Issues guide.

Link to this sectionAxelera Driver Installation#

1. Add the Axelera repository key:

   sudo sh -c "curl -fsSL https://software.axelera.ai/artifactory/api/security/keypair/axelera/public | gpg --dearmor -o /etc/apt/keyrings/axelera.gpg"

2. Add the repository to apt:

   Choose the appropriate snippet from below to match the OS being used.

   # Ubuntu 22.04
   sudo sh -c "echo 'deb [signed-by=/etc/apt/keyrings/axelera.gpg] https://software.axelera.ai/artifactory/axelera-apt-source ubuntu22 main' > /etc/apt/sources.list.d/axelera.list"

   # Ubuntu 24.04
   sudo sh -c "echo 'deb [signed-by=/etc/apt/keyrings/axelera.gpg] https://software.axelera.ai/artifactory/axelera-apt-source ubuntu24 main' > /etc/apt/sources.list.d/axelera.list"

3. Install the SDK and load the driver:

   sudo apt update
   sudo apt install -y metis-dkms=1.4.16
   sudo modprobe metis

pip install axelera-devkit==1.6.0 --extra-index-url https://software.axelera.ai/artifactory/api/pypi/axelera-pypi/simple
pip install axelera-rt==1.6.0 --extra-index-url https://software.axelera.ai/artifactory/api/pypi/axelera-pypi/simple

Link to this sectionExporting YOLO Models to Axelera#

The Axelera format supports the Export, Predict, and Validate modes. Inference and validation run on Axelera Metis AIPU hardware. Export your model, then load the exported model to run inference or validate its accuracy.

from ultralytics import YOLO

# Load a YOLO26 model
model = YOLO("yolo26n.pt")

# Export the model to Axelera format
model.export(format="axelera")  # creates 'yolo26n_axelera_model'

from ultralytics import YOLO

# Load the exported Axelera model
model = YOLO("yolo26n_axelera_model")

# Run inference
results = model("https://ultralytics.com/images/bus.jpg")

from ultralytics import YOLO

# Load the exported Axelera model
model = YOLO("yolo26n_axelera_model")

# Validate accuracy on the COCO8 dataset
metrics = model.val(data="coco8.yaml")

Link to this sectionExport Arguments#

For all export options, see the Export Mode documentation.

Link to this sectionOutput Structure#

yolo26n_axelera_model/
├── yolo26n.axm                  # Axelera model file
├── compiler_config_final.toml  # Compiler configuration used for the build
└── metadata.yaml               # Model metadata (classes, image size, etc.)

Link to this sectionAxelera AI Benchmarks#

The Metis AIPU maximizes throughput while minimizing energy consumption.

Benchmarks based on Axelera AI data. Actual FPS depends on model size, batching, and input resolution.

Link to this sectionReal-World Applications#

Ultralytics YOLO on Axelera hardware enables advanced edge computing solutions:

• Smart Retail: Real-time object counting and heatmap analytics for store optimization.
• Industrial Safety: Low-latency PPE detection in manufacturing environments.
• Drone Analytics: High-speed object detection on UAVs for agriculture and search-and-rescue.
• Traffic Systems: Edge-based license plate recognition and speed estimation.

Link to this sectionRecommended Workflow#

1. Train your model using Ultralytics Train Mode
2. Export to Axelera format using model.export(format="axelera")
3. Validate accuracy with yolo val to verify minimal quantization loss
4. Predict using yolo predict for qualitative validation
5. Deploy to a high-performance end-to-end pipeline without PyTorch dependency — see the YOLO on Voyager SDK examples for composable Python pipelines using axelera-rt

Link to this sectionDevice Health Check#

Verify your Axelera device is functioning properly:

# if axdevice cannot be found, please run at least one inference (see above) to ensure the required packages are installed
axdevice

For detailed diagnostics, see the AxDevice documentation.

Link to this sectionMaximum Performance#

This integration uses single-core configuration for compatibility. For production requiring maximum throughput, the Axelera Voyager SDK offers:

• Multi-core utilization (quad-core Metis AIPU)
• Streaming inference pipelines
• Tiled inferencing for higher-resolution cameras

See the model-zoo for FPS benchmarks or contact Axelera for production support.

Link to this sectionKnown Issues#

For support, visit the Axelera Community.

Link to this sectionFAQ#

Link to this sectionWhat YOLO versions are supported on Axelera?#

The Voyager SDK supports export of YOLOv8, YOLO11, and YOLO26 models. See Supported Tasks for per-model task availability.

Link to this sectionCan I deploy custom-trained models?#

Yes. Any model trained using Ultralytics Train Mode can be exported to the Axelera format, provided it uses supported layers and operations.

Link to this sectionHow does INT8 quantization affect accuracy?#

Axelera's Voyager SDK automatically quantizes models for the mixed-precision AIPU architecture. For most object detection tasks, the performance gains (higher FPS, lower power) significantly outweigh the minimal impact on mAP. Quantization takes seconds to several hours depending on model size. Run yolo val after export to verify accuracy.

Link to this sectionHow many calibration images should I use?#

We recommend 100 to 400 images. More than 400 provides no additional benefit and increases quantization time. Experiment with 100, 200, and 400 images to find the optimal balance.

Link to this sectionWhere can I find the Voyager SDK?#

The SDK, drivers, and compiler tools are available via the Axelera Developer Portal.