Blog
Launchpad
Documentation
Axelera Website
Store

New Post
Login

Welcome to the Axelera® AI Community

Ask questions, get inspired, share your projects and get involved in AI

The Smarter Spaces Project Challenge with Axelera AI and Orange Pi

Using Metis + Orange Pi, we’re challenging you to create an offline, vision-powered edge AI system that makes the spaces we live in, work in, play and visit so much smarter.

Connect

Chat, ask questions, help out, get inspired

Blog

News, blogs, updates and announcements

Launchpad

Share your feedback, feature requests, ideas

📌 Pinned

👋 Say Hello - Introduce Yourself to the Axelera AI Community

Recent activity
Help others
Categories

J

juliannarvaezCadet

Metis M.2

RPI 5 external power M.2 Hat with Metis 2

Another RPI 5 question. Have any developers attempted to overcome the power limitation issues with the RPI 5 by using the USB C PD along with a external powered RPI 5 M2 Hat?I have been considering using the Geekworm X1001 PCIe to M.2 HAT Key-M NVMe

141

5 hours ago

S

shashibhatCadet

Project Challenge

project SafeHaven: AI-Driven Offline Security for Every Home

Hello All,I am so glad to be part of this community. This is my first time participating in this . I am very excited. Did you know nearly 30% of home break-ins happen through unlocked doors or open garages?After a long day, you finally lie down, and

juliannarvaezCadet

Issue with RPI 5 DMA and firmware upgrade

I have a metis M.2 device running on a RPI M.2 hat using the 1.2.4 device driver and the 1.4.2 SDK. However, when I tried to run inference, I ran into a DMA transfer issue. I tried to fix this by updating the AIPU firmware but the DMA transfer issue

meva-ysfCadet

Can not Enable Update

Hi,I have 3 axelera metis m2 device. I could not enable update for all of them. I have Voyager SDK 1.5.2 version that installed successfully. When i enter the command “./enable_bootloader_update.sh" it gives an error such as “Device communication tim

JulianaAxelera Team

CES 2026: From AI Hype to Inference Reality at the EdgeBlog

CES has always been a bellwether for where technology wants to go. CES 2026 felt different. This year wasn’t defined by a single breakthrough announcement or the unveiling of a bigger, shinier model. Instead, it marked a quieter, but more important s

FreezerJohnEnsign

Hi all!I’m currently trying to setup a simple pipeline with yolo pose + tracker.The attached YAML works fine, but how to link the tracker results back to the tracked object?It seems the trackers meta data does not contain any reference to the tracked

calebaurorionCadet

AurorionEdge: Equipment Arrival and Unbox!

Did a quick unbox and carved out a tiny corner of my space to start staging everything. This is officially the beginning of the build! For the first phase, I’m keeping things intentionally simple and solid:Get everything unboxed and inventoried Ins

akash_vertexCadet

Help Needed: InsightFace Deployment on Axelera Device

Hello everyone,I am new to Axelera and working with a Metis device (4 GiB, PCIe, Voyager SDK). Device: metis-0:1:0 Memory: 4GiB Clock: 800MHz SDK: voyager-sdk I am trying to deploy the InsightFace model for face recognition and would appreciate guid

271

5 days ago

DenovoCadet

Project Challenge

A.B.C. ( A.I. Book Cataloguer )

Hello everyone! This is our first thread in the community, and we’re excited to share what we’re building with the challenge kit! Project titleA.B.C. ( A.I. Book Cataloguer ) What you’ll be buildingWe’re developing a next-generation tabletop station

dilip.mCadet

Project RehabVision - Update

Hi all! 👋We’re excited to share our first progress update on our camera-based Physiotherapy Assistant project. The hardware has been successfully set up, and we’re currently finalizing the development environment and system architecture.We’ve begun p

meva-ysfCadet

Can not Enable Update

Hi,I have 3 axelera metis m2 device. I could not enable update for all of them. I have Voyager SDK 1.5.2 version that installed successfully. When i enter the command “./enable_bootloader_update.sh" it gives an error such as “Device communication tim

FreezerJohnEnsign

Hi all!I’m currently trying to setup a simple pipeline with yolo pose + tracker.The attached YAML works fine, but how to link the tracker results back to the tracked object?It seems the trackers meta data does not contain any reference to the tracked

akash_vertexCadet

Help Needed: InsightFace Deployment on Axelera Device

Hello everyone,I am new to Axelera and working with a Metis device (4 GiB, PCIe, Voyager SDK). Device: metis-0:1:0 Memory: 4GiB Clock: 800MHz SDK: voyager-sdk I am trying to deploy the InsightFace model for face recognition and would appreciate guid

mardistalCadet

axelera M2 and radxa 5B+

I am using armbian 6.1.115 after installing everything lspci -vv0001:11:00.0 Processing accelerators: Axelera AI Metis AIPU (rev 02) Subsystem: Axelera AI Metis AIPU (rev 02) Control: I/O- Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr-

VitoCadet

Vito T: Smarter Spaces Projects

Hi everyone! 👋We’re happy to kick off the year by sharing a first update on our Smarter Spaces project.The kit has arrived safely, and over the past weeks we’ve been focusing on the initial setup and preparing our development environment. We’re curre

tchretienEnsign

Metis Compute Board – Persistent ERROR: No devices found even after reboot

Hello,I am facing an issue with a Metis Compute Board where any inference command (or any command using the accelerator) immediately fails with the error:ERROR: No devices found This happens regardless of the model or the command I run.Yesterday, I m

15115

10 days ago

SpannerAxelera Team

LLMs, NLP, Neural Networks

Which models are you using with Metis? Or want to use.

I’m interested in hearing from everyone here about which models you’re successfully using with your Metis device and Voyager SDK, and which ones you’d like to see being officially supported.This could be really useful info in terms of prioritisation

tchretienEnsign

Question on the developpement outside the SDK

Hello,I’m currently working with the Metis Compute Board and the Voyager SDK, and I had a question regarding development outside of the SDK.Is it possible to run a script like a custom inference or a similar script directly on the board without going

MArioEnsign

Nature of flatten operation

Hello,Following the question I had on running a GEMM only model, I have settled for a model that has Id Conv → Flatten → Gemm . I was wondering if the Flatten operation is just rearranging some pointer values or if it is doing a memory operation (lik

dhd6682Cadet

Missing libaxruntime.so

Hi,I'm using NanoPC-T6. I followed the Https://support.axelera.ai/hc/en-us/articles/31859388491794-Bring-up-Voyager-SDK-in-NanoPC-T6 you sent me. However, when I proceed with the test, the test will not proceed with the following error.https://commun

363

13 days ago