Axelera AI

@AxeleraAI

A powerful, efficient, cost-effective, and user-friendly hardware and software AI platform to accelerate computer vision in edge devices.

Eindhoven, Netherlands

Joined July 2021

Axelera AI
@AxeleraAI
12h
You don't have to adopt our pipeline to use Axelera tech. AxRuntime for model-level inference in C++ or Python. AxInferenceNet for custom pre and post-processing. InferenceStream for the full YAML route. Pick your level: eu1.hubs.ly/H0xF4zb0
Axelera AI
@AxeleraAI
Aug 25
A card that won't enumerate. A throughput ceiling you can't account for. A blank YAML file. Voyager Wingman writes the pipeline from a plain-language description, runs it on your device, and helps you dig into what's blocking you. Free: eu1.hubs.ly/H0xHqhQ0
Axelera AI
@AxeleraAI
Aug 20
Person-of-interest ID and weapon detection running simultaneously across two 8K feeds. Three Axelera Server 150p cards, 48 AIPU cores, 1,440+ model inferences a second at 30-58W per card. Full build: eu1.hubs.ly/H0xF4Bb0
Axelera AI
@AxeleraAI
Aug 19
Model accuracy dropped after compiling? In our community threads it usually isn't the quantization. More often it's RGB where RGBA was expected, or post-processing the compiler detached. Run the same dataset through torch, torch-aipu and gst to find out: eu1.hubs.ly/H0xF5tn0
Axelera AI
@AxeleraAI
Aug 18
Medical imaging data is exploding, leaving trained radiologists facing severe burnout and long backlogs. AI doesn't replace doctors, it empowers them. Our partner @MicronTech highlights how Axelera Metis® AIPUs and Micron LPDDR4 memory deliver real-time scan analysis right at