Skip to main content

Feature Request Pipeline

Filter by Status

Filter by Type

24 Posts

S
Cadet
sanket-shahCadet

Monocular 3D Object Detection on Metis at 24.5 FPS — full pipeline, single core, realtimeNew

Sharing my first project on Axelera Metis: end-to-end monocular 3D object detection running at 24.5 FPS on a single AIPU core, with a CPU host and no GPU anywhere in the pipeline.What it does Takes a single camera image and predicts 3D bounding boxes for every car, pedestrian and cyclist in the scene  position, dimensions and orientation , in real time. Built on MonoCon (CVPR 2022) with a DLA-34 backbone, evaluated on KITTI driving sequences.How it is split The model had to be divided at a hard compiler boundary. AttnBatchNorm2d contains a ReduceMean op that Voyager cannot quantize, so the pipeline is:AIPU: backbone + neck + fused HeadConv1 (64 to 576 channels, single output tensor) CPU host: AttnBatchNorm2d + ReLU + 1x1 convs, implemented in hand-written C++ PerformanceStage Time Preprocess + Quantize 1.4 ms AIPU inference 31 ms Dequantize 6.5 ms Head (C++) 22 ms Decode + NMS 1 ms Sequential total 62 ms / 16 FPS Pipelined throughput 41 ms / 24.5 FPS Pipelined throughput uses a two-thread producer-consumer design: the AIPU processes frame N+1 while the CPU decodes frame N concurrently.Key findings during deployment A few things that are not in the documentation and took real time to figure out: per_tensor_histogram (default) silently clips HeadConv1 activations — true range is roughly -1350 to +1200, the histogram scheme covers only -250 to +250. Zero detections until switching to per_tensor_min_max. Multi-output graphs get their outputs sorted alphabetically by the compiler. Discovered by comparing per-tensor statistics against a PyTorch reference. Fixed by fusing all nine head convs into one 64 to 576 conv with a single output tensor. axrArgument.fd must be -1 for host-pointer mode. Setting it to 0 silently produces zero output with AXR_SUCCESS returned. The first 2-3 inference calls return stale output regardless of input. Warm-up with dummy frames is required before trusting results. ONNXRuntime was taking 55ms on a 24,000-parameter subgraph , not because of arithmetic but because of per-node dispatch overhead across ~150 ops. Replaced with a preallocated C++ implementation: 55ms to 22ms. Repo Everything is open source: PyTorch model, ONNX export scripts,Voyager compile script, C++ inference library with 3D box and bird's-eye view visualization.https://github.com/sanket-pixel/monocon-metisHappy to answer questions on any part of the deployment.Bonus discussion point :Running the backbone+neck+HeadConv1 graph alone via axrunmodel hits 90 FPS on four cores and 40 FPS on a single core. The compiled model in this project uses aipu_cores_used=1, resources_used=0.25,  straightforward but not necessarily optimal. There is likely headroom in the compiler configuration that this project has not fully explored: tiling depth, DFS search constraints, IMC double buffer pipelining, and grouping IFDW tasks are all knobs that affect how efficiently the compiler maps the graph onto the MVM array. If anyone has found configurations that push closer to the axrunmodel ceiling on a similarly sized graph, would be very interested to hear what worked. Happy to discuss.  

0
S
Cadet
Forum|Forum|3 days ago
D
Ensign
doritosEnsign

Jetson Orin NX 16GB + Metis M.2 + ZED X on a PREEMPT_RT kernel full guideNew

Wrote up the complete recipe for getting the Metis running on a real-time kernel alongside a ZED X stereo camera: in-tree driver (no OOT vermagic headaches), 49 fps yolov5s on 1080p at ~14% CPU, and a full sensor fusion sample running detection + GPU depth + point cloud + IMU pose + skeleton tracking concurrently at 46–53 fps — detector costs the GPU essentially zero.Covers the ugly parts too: the DTBO trap, the PCIE_LINK_WAIT_MAX_RETRIES brownout fix, the GST_PLUGIN_FEATURE_RANK workaround for file/RTSP sources, and vermagic discipline end to end.All numbers are live measurements on the reference unit, not projections. Full article (free link, no paywall):https://medium.com/@silicondoritos/jetson-metis-zed-x-inference-on-a-real-time-kernel-ee49c17b5c6f?source=friends_link&sk=d255fc3135f4527de57f606a95a54cb6 Repo (Apache 2.0) — make ignite gets you from zero to flashed: https://github.com/silicondoritos/jetson-rt-stack There you can see the sample application showing the stuff you can do with the metis running yolo8l and the zedx camera sdk. You can see the labels, distances, boxes, the arrow showing the calculated direction of the object and the 3D volumes for detected objects. All in real time. Happy to answer questions here or in the repo issues.  

0
D
Ensign
Forum|Forum|1 month ago
D
Cadet
DebeshAICadet

AINew

Hello Everyone My Name is D.M. .. As a period am quite optimistic and comfortable to complex situations. I have a keen interest in Artificial intelligence and Coding. I wanted to make a Mental Health Peace app that can detect the condition of humans mental condition and try to heal it. The human brain is the most powerful and mist Weakest thing in the world, Please give me some ideas that I can develop it more better.... Thank you Everyone. 

0
D
Cadet
Forum|Forum|1 month ago
N
Cadet
NaveenCadet

Quantum computing software tool kit connected with AINew

Recently i developed quantum computing software tool kit connected with AI This tool name is AQC tool kit This is advanced software tool kit  

0
N
Cadet
Forum|Forum|1 month ago
S
Cadet
spectral369Cadet

Model Request - IBM's GraniteNew

Hello,As per original POST I’d like to request compatibility for IBM’s Granite modelsEmbedding and LLM ModelThank you,Peter

0
S
Cadet
Forum|Forum|1 month ago
M
Cadet
MohCadet

can i get helpNew

I have idea to make a bottle which increase subscriber and views hour on YouTube those you are interst plese mail me

0
M
Cadet
Forum|Forum|1 month ago
V
Ensign
VitoEnsign

Case Study NemaMedbot/MikyRobotNew

Hi Spanner, I’d like to follow up regarding the potential case study around Nema MedBot / Miky RobotIn the meantime, the project has evolved significantly both from a business and technological perspective, particularly regarding the integration of the solution with Orange Pi and the Axelera Metis AI Accelerator.At the same time, we are opening new opportunities connected to crowdfunding, commercial development, and the positioning of the project within the field of AI applied to wellness, health, posture, nutrition, and advanced aesthetics.For this reason, I believe it could now be valuable to develop the case study in a more structured and strategic way, highlighting the recognition received through the Axelera award, the practical application of your technology, and the overall communication and industrial potential of the project.I completely understand that over the past months there have been internal priorities and updates related to the platform and website. I simply wanted to understand whether the interest in this collaboration is still active and whether it makes sense to begin defining a possible operational direction.If useful, I can also prepare a concise document with a technical overview, project vision, and the key elements that could support the development of the case study and facilitate any internal evaluation.

0
V
Ensign
Forum|Forum|1 month ago
A
Cadet
Andred7Cadet

Andred7New

Design me the following with the name ANDRED7 on all.1. An hybrid drone that is equipped with a sonar, a very good day and night video camera for streaming live video feeds to head office, a solar that can run for 7 days, get go's coordination and send info via satellite to head office and other hybrid equipment and the drone should be able to communicate and give orders to other hybrids. 2. The vessel that is equipped with the follow: 5 skimmer boats attached to both sides of the vessel. The skimmer boats are released by the vessel and on its return with the help of sensors positions itself perfectly so that the vessel can attach it. The skimmer boats are controlled by a pyp that can extract and pull back, the pyp is switched on by the vessel that sucks up the oil. The boom. It can extract and be pulled back in. The lengIs is given by the drone. The boom has sensors that helps to navigate the skimmers and to firm a dam around the oil.. The crain, it is used to attach its arms to a submarine and a big pyp. On top of the crain is a good day and night video camera for streaming live video to head office. The submarine is equipped with a sensor, Good day and night video camera for streaming live video. The submarine is used to find any damage to the vessel that made the spill and weld the damages plus the arms of the submarine can also attach a long pyp to sunken ships that contain oil in order to suck op the oil. All equipment on the vessel all have solar, can communicate to each other and head office plus be able to attach itself to a charging port and detach itself.Once the vessel is full off oil the vessel returns to the port where it positions itself under a crain with the help of sensors. The crains arms attach a pyp to the vessel and pumps out the oil into containers. The crain also has a solar, can work with sensors that's on the vessel and the containers. 

1
A
Cadet
Forum|Forum|2 months ago
S
Cadet
SiegfriedCadet

uv buildImplemented

uv (pip alternative) build for the voyager-sdk. Many organizations are switching over to uv due to its many benefits over pip. This would speed up setup of the sdk and allow easier merging with development environments  

2
Spanner
Forum|Forum|3 months ago
N
Cadet
Necrose99Cadet

windows drivers scriptNew

#Get-MetisDrivers.ps1## normally bcd edit allow unsigned drivers ... on github  Voyager SDK  every reboot ... kills bitlocker secboot.. etc... ### required wdk winget install Microsoft.WindowsSDK.10.0.22621#Requires -RunAsAdministrator<#.SYNOPSIS    Downloads, unpacks, and test-signs Axelera Metis M.2 AIPU drivers locally..DESCRIPTION    Step 1 of Axelera Metis driver installation:      - Downloads MetisDriver and optionally Switchtec-kmdf archives      - Extracts to a staging directory      - Generates a self-signed test certificate (if not already present)      - Signs all .sys/.cat/.inf driver files with the local cert      - Enables TESTSIGNING boot mode if not already active.PARAMETER DestDir    Directory where archives and unpacked drivers will be staged.    Default: $env:USERPROFILE\MetisDrivers.PARAMETER IncludeSwitchtec    Switch to also download the Switchtec-kmdf driver (required only for    the 4-Metis PCIe board, not needed for single M.2 Metis)..PARAMETER CertSubject    Subject name for the generated test-signing certificate.    Default: "MetisTestSign".EXAMPLE    # Single M.2 Metis (most common homelab case)    .\Get-MetisDrivers.ps1.EXAMPLE    # 4-port PCIe board    .\Get-MetisDrivers.ps1 -IncludeSwitchtec.EXAMPLE    # Custom staging directory    .\Get-MetisDrivers.ps1 -DestDir D:\Drivers\Metis -IncludeSwitchtec#>[CmdletBinding()]param(    [string]$DestDir        = "$env:USERPROFILE\MetisDrivers",    [switch]$IncludeSwitchtec,    [string]$CertSubject    = "MetisTestSign")Set-StrictMode -Version Latest$ErrorActionPreference = "Stop"# ---------------------------------------------------------------------------# Helpers# ---------------------------------------------------------------------------function Write-Step([string]$Msg) {    Write-Host "`n==> $Msg" -ForegroundColor Cyan}function Write-OK([string]$Msg) {    Write-Host "    [OK] $Msg" -ForegroundColor Green}function Write-Warn([string]$Msg) {    Write-Host "    [!!] $Msg" -ForegroundColor Yellow}# ---------------------------------------------------------------------------# URLs# ---------------------------------------------------------------------------$BaseUrl   = "https://software.axelera.ai/artifactory/axelera-win/driver/1.3.x"$Downloads = [ordered]@{    "MetisDriver-1.3.1.zip"         = "$BaseUrl/MetisDriver-1.3.1.zip"    "switchtec-kmdf-0.7_2019.zip"   = "$BaseUrl/switchtec-kmdf-0.7_2019.zip"}# ---------------------------------------------------------------------------# 0. Preflight# ---------------------------------------------------------------------------Write-Step "Preflight checks"# Ensure WDK signtool is available (ships with Windows SDK / WDK)$SignTool = (Get-Command signtool.exe -ErrorAction SilentlyContinue)?.Sourceif (-not $SignTool) {    # Fallback: search common SDK paths    $CandidatePaths = @(        "${env:ProgramFiles(x86)}\Windows Kits\10\bin\*\x64\signtool.exe"        "${env:ProgramFiles}\Windows Kits\10\bin\*\x64\signtool.exe"    )    $SignTool = Resolve-Path $CandidatePaths -ErrorAction SilentlyContinue |                Sort-Object -Descending |                Select-Object -First 1 -ExpandProperty Path}if (-not $SignTool) {    Write-Warn "signtool.exe not found. Install the Windows SDK / WDK."    Write-Warn "  winget install Microsoft.WindowsSDK.10.0.22621"    Write-Warn "Continuing — signing step will be skipped."}else {    Write-OK "signtool: $SignTool"}# Makecert / New-SelfSignedCertificate availability$HasPKI = [bool](Get-Command New-SelfSignedCertificate -ErrorAction SilentlyContinue)Write-OK "New-SelfSignedCertificate available: $HasPKI"# ---------------------------------------------------------------------------# 1. Create staging directory# ---------------------------------------------------------------------------Write-Step "Creating staging directory: $DestDir"$null = New-Item -ItemType Directory -Force -Path $DestDir$ArchiveDir  = Join-Path $DestDir "archives"$ExtractDir  = Join-Path $DestDir "extracted"$null = New-Item -ItemType Directory -Force -Path $ArchiveDir, $ExtractDirWrite-OK "Directories ready."# ---------------------------------------------------------------------------# 2. Download archives# ---------------------------------------------------------------------------Write-Step "Downloading driver archives"$ToDownload = @("MetisDriver-1.3.1.zip")if ($IncludeSwitchtec) { $ToDownload += "switchtec-kmdf-0.7_2019.zip" }foreach ($FileName in $ToDownload) {    $Url        = $Downloads[$FileName]    $OutFile    = Join-Path $ArchiveDir $FileName    if (Test-Path $OutFile) {        Write-Warn "$FileName already present — skipping download."        continue    }    Write-Host "    Downloading $FileName ..." -NoNewline    try {        $ProgressPreference = 'SilentlyContinue'   # dramatically faster Invoke-WebRequest        Invoke-WebRequest -Uri $Url -OutFile $OutFile -UseBasicParsing        $ProgressPreference = 'Continue'        Write-Host " done." -ForegroundColor Green    }    catch {        Write-Host " FAILED." -ForegroundColor Red        Write-Warn "Could not download $FileName : $_"        Write-Warn "Download manually from: $Url"    }}# ---------------------------------------------------------------------------# 3. Extract archives# ---------------------------------------------------------------------------Write-Step "Extracting archives"Get-ChildItem -Path $ArchiveDir -Filter "*.zip" | ForEach-Object {    $Zip     = $_.FullName    $Target  = Join-Path $ExtractDir $_.BaseName    if (Test-Path $Target) {        Write-Warn "$($_.Name) already extracted — skipping."        return    }    Write-Host "    Expanding $($_.Name) ..."    Expand-Archive -Path $Zip -DestinationPath $Target -Force    Write-OK "Extracted to: $Target"}# ---------------------------------------------------------------------------# 4. Create / retrieve test-signing certificate# ---------------------------------------------------------------------------Write-Step "Test-signing certificate"$CertStore  = "Cert:\LocalMachine\My"$ExistingCert = Get-ChildItem $CertStore |                Where-Object { $_.Subject -like "*$CertSubject*" } |                Select-Object -First 1if ($ExistingCert) {    Write-OK "Re-using existing cert: $($ExistingCert.Thumbprint)"    $Cert = $ExistingCert}elseif ($HasPKI) {    Write-Host "    Creating self-signed certificate '$CertSubject' ..."    $Cert = New-SelfSignedCertificate `        -Subject        "CN=$CertSubject" `        -Type           CodeSigningCert `        -CertStoreLocation $CertStore `        -KeySpec        Signature `        -HashAlgorithm  SHA256 `        -NotAfter       (Get-Date).AddYears(10)    # Also install into Trusted Publishers + Root so Windows trusts test-signed drivers    $CertPEM = Export-Certificate -Cert $Cert -FilePath (Join-Path $DestDir "$CertSubject.cer") -Type CERT    Import-Certificate -FilePath $CertPEM.FullName -CertStoreLocation "Cert:\LocalMachine\Root"          | Out-Null    Import-Certificate -FilePath $CertPEM.FullName -CertStoreLocation "Cert:\LocalMachine\TrustedPublisher" | Out-Null    Write-OK "Certificate created and installed. Thumbprint: $($Cert.Thumbprint)"}else {    Write-Warn "Cannot create certificate (New-SelfSignedCertificate unavailable)."    Write-Warn "Signing step will be skipped."    $Cert = $null}# ---------------------------------------------------------------------------# 5. Sign drivers# ---------------------------------------------------------------------------Write-Step "Signing driver files"if ($SignTool -and $Cert) {    $DriverFiles = Get-ChildItem -Path $ExtractDir -Recurse -Include "*.sys","*.cat","*.dll" |                   Where-Object { -not $_.PSIsContainer }    if ($DriverFiles.Count -eq 0) {        Write-Warn "No signable driver files found in $ExtractDir"    }    else {        foreach ($File in $DriverFiles) {            Write-Host "    Signing: $($File.Name) ..."            & $SignTool sign `                /sha1  $Cert.Thumbprint `                /fd    sha256 `                /tr    "http://timestamp.digicert.com" `                /td    sha256 `                /v     $File.FullName 2>&1 | ForEach-Object { "      $_" }            if ($LASTEXITCODE -ne 0) {                Write-Warn "signtool returned $LASTEXITCODE for $($File.Name) — check output above."            }            else {                Write-OK $File.Name            }        }    }}elseif (-not $SignTool) {    Write-Warn "Skipping signing: signtool.exe not found."}elseif (-not $Cert) {    Write-Warn "Skipping signing: no certificate available."}# ---------------------------------------------------------------------------# 6. Enable TESTSIGNING boot mode# ---------------------------------------------------------------------------Write-Step "Boot configuration — TESTSIGNING"$BcdOutput  = & bcdedit /enum '{current}' 2>&1$IsTestSign = $BcdOutput -match "testsigning\s+Yes"if ($IsTestSign) {    Write-OK "TESTSIGNING already enabled."}else {    Write-Host "    Enabling TESTSIGNING ..."    & bcdedit /set testsigning on | Out-Null    if ($LASTEXITCODE -eq 0) {        Write-OK "TESTSIGNING enabled. A reboot is required before installing the driver."    }    else {        Write-Warn "bcdedit failed (LASTEXITCODE=$LASTEXITCODE). Run as Administrator?"    }}# Also disable Secure Boot enforcement for test-signed drivers (Disable Integrity Checks)# Only uncomment if you are on a non-Secure-Boot system / dev machine:# & bcdedit /set nointegritychecks on# ---------------------------------------------------------------------------# 7. Summary# ---------------------------------------------------------------------------Write-Step "Summary"Write-Host ""Write-Host "  Staging root   : $DestDir"                           -ForegroundColor WhiteWrite-Host "  Archives       : $ArchiveDir"                        -ForegroundColor WhiteWrite-Host "  Extracted      : $ExtractDir"                        -ForegroundColor Whiteif ($Cert) {Write-Host "  Cert thumbprint: $($Cert.Thumbprint)"               -ForegroundColor White}Write-Host ""Write-Host "  Next steps:"                                         -ForegroundColor YellowWrite-Host "    1. Reboot if TESTSIGNING was just enabled."        -ForegroundColor YellowWrite-Host "    2. In Device Manager, right-click the Metis"       -ForegroundColor YellowWrite-Host "       device -> Update driver -> Browse my computer"  -ForegroundColor YellowWrite-Host "       -> point at: $ExtractDir\MetisDriver-1.3.1"    -ForegroundColor Yellowif ($IncludeSwitchtec) {Write-Host "    3. Repeat for the Switchtec controller using:"     -ForegroundColor YellowWrite-Host "       $ExtractDir\switchtec-kmdf-0.7_2019"           -ForegroundColor Yellow}Write-Host ""

2
N
Cadet
Forum|Forum|4 months ago
V
Ensign
VitoEnsign

Nema AI - Medbot - Miky robotNew

NEMA MedBot – Edge Identity Workflow with Metis 2 Acceleration RoadmapBody:We are presenting the current prototype of NEMA MedBot / Mickey Robot developed by AtomC.This stage validates a fully on-device identity recognition pipeline running on Orange Pi hardware. The system performs real-time acquisition, local inference and dashboard update without any cloud dependency.The architecture has been designed to integrate Axelera Metis® 2 as the dedicated hardware acceleration layer for inference stages. The current prototype confirms end-to-end workflow stability and modular separation of perception and orchestration layers.Next steps include progressive offloading of supported inference blocks to Metis 2 via the Voyager toolchain, enabling reduced latency, deterministic performance and scalable multi-model deployment.The project is part of an ongoing commercial R&D initiative targeting healthcare and posture analysis environments, with clinical validation planned in collaboration with a medical partner in the province of Brescia.We appreciate the opportunity provided by Axelera AI and look forward to further technical collaboration.https://github.com/VITOTRAVE/nema-medbot-edge-demohttps://youtu.be/AuaEN8rGLGAwww.aromc135.comwww.ciaochili.ithttps://www.linkedin.com/posts/dott-prof-vito-traversa-66a8682b0_axeleraai-metis2-edgeai-activity-7433985494352543744-iY85 

0
V
Ensign
Forum|Forum|4 months ago
V
Ensign
VitoEnsign

Nema-Medbot-MikyRobotNew

AXELERA CHALLENGE – PROJECT UPDATEWe are progressing on the development of NEMA–MedBot–Miky, a modular robotic platform for assistance, human–robot interaction, and embodied edge AI experimentation.NEMA is our proprietary artificial intelligence, developed in-house, designed to orchestrate perception, reasoning, and action across our robotic systems.Recent progress:Hardware integration of Axelera Metis2 on Orange Pi 5 Plus via PCIe Successful device enumeration on the PCIe bus Voyager SDK installation in progress to enable accelerated on-device inferenceThe architecture we are building is edge-first:Orange Pi handles ROS2, sensors, actuators, and control logic Metis2 is dedicated to neural inference (vision, perception, multimodal models) NEMA coordinates AI pipelines and decision-makingThis approach enables low latency, efficient resource usage, and a scalable, industrial-grade architecture.NEMA–MedBot–Miky is not a maker project.We are a real startup building a platform with commercial and industrial objectives.Part of the codebase will remain proprietary. We are open to strategic and commercial partnerships.Next steps:First accelerated inference on Metis2 Vision → AI → ROS → motor pipeline Head movement and interaction testsWe thank Axelera for supporting the edge AI ecosystem and for the opportunity to participate in the challenge.MINI TECHNICAL REPORTNEMA–MedBot–Miky – Technical Progress UpdateAbstractNEMA–MedBot–Miky is a modular edge-AI robotic platform for assistance, human–robot interaction, and embodied intelligence research. The system combines Orange Pi 5 Plus for control and ROS2 with the Axelera Metis2 accelerator for neural inference. A proprietary AI engine (NEMA) orchestrates perception, reasoning, and action. The architecture is designed for low latency, modularity, and scalability, targeting real-world industrial and assistive applications.Hardware StatusOrange Pi 5 Plus operational Axelera Metis2 installed via PCIe Metis2 device enumerated on PCIe bus USB Bluetooth dongle and external speaker integratedSoftware StatusArmbian Linux running on Orange Pi ROS2 workspace initialized Neural TTS (Piper) operational Automatic audio routing and Bluetooth reconnection implemented Voyager SDK installation in progressSystem ArchitectureOrange Pi → ROS2, sensors, actuators, control Metis2 → accelerated neural inference NEMA → AI orchestration and decision layerCurrent CapabilitiesVoice output with neural TTS Automatic startup greeting Modular software structureNext Steps (24–72h)Complete Voyager SDK installation Run first inference demos on Metis2 Integrate vision output with ROS2 Enable head motor controlNotes on IP and Commercial StrategyReal startup project Partial proprietary codebase Focus on commercial and industrial partnerships

0
V
Ensign
Forum|Forum|4 months ago
V
Ensign
VitoEnsign

Project Update: NEMA AI Integration on MedBot and Early Miky Robot PrototypingNew

Project Update – MedBot / Miky RobotWe are currently testing our proprietary artificial intelligence, NEMA, and adapting some of its capabilities to the MedBot project.In particular, we are integrating NEMA on Orange Pi together with the Metis accelerator board by Axelera, with the goal of equipping MedBot with a new layer of intelligence dedicated to assistance, interaction, and user support.The same NEMA AI is also being integrated into Miky Robot, conceived as a humanoid interface for MedBot.At this early stage, we are working on the first hardware components and their integration with artificial intelligence.Current Status of Hardware DevelopmentWe are 3D printing the first parts of the robot, especially the head and some structural components.We are performing printing iterations and mechanical tests.In parallel, we are testing the integration between NEMA and the Axelera hardware platform.We have also started developing the case for the monitor that will host the Axelera mainboard, but currently only some parts of the case are in the prototyping phase.Realistic Goals by the End of FebruaryBy the end of February, we expect to have:an initial working integration of NEMA on MedBot;a partial prototype of Miky Robot, likely including:the head with AI capabilities and sensors,some structural components,and, if possible, an early preliminary version of arms and hands;a first partial version of the mainboard case, not yet complete.This is therefore an early prototyping phase, focused on validating the integration between AI and hardware rather than delivering a complete system.We can share some work-in-progress images of the 3D printing phases and hardware components currently under development, to show the real status of the project.We will continue sharing updates as the system evolves from an initial prototype toward a more integrated solution.Best regards,Vito Traversa 

0
V
Ensign
Forum|Forum|5 months ago
A
Cadet
alsuttonCadet

Problem with axdevice --refresh causing NVMe drives to be stopped on a running systemImplemented

Putting this up for folk who may hit a similar issue.If you have a machine which has a single root PCIe device, where the output of lspci -tv looks something like this;alsutton@svr204:~$ lspci -tv-[0000:00]-+-00.0 Intel Corporation 8th Gen Core Processor Host Bridge/DRAM Registers +-02.0 Intel Corporation CoffeeLake-S GT2 [UHD Graphics 630] +-08.0 Intel Corporation Xeon E3-1200 v5/v6 / E3-1500 v5 / 6th/7th/8th Gen Core Processor Gaussian Mixture Model +-14.0 Intel Corporation Cannon Lake PCH USB 3.1 xHCI Host Controller +-14.2 Intel Corporation Cannon Lake PCH Shared SRAM +-16.0 Intel Corporation Cannon Lake PCH HECI Controller +-1b.0-[01]----00.0 Micron/Crucial Technology P2 [Nick P2] / P3 / P3 Plus NVMe PCIe SSD (DRAM-less) +-1f.0 Intel Corporation B360 Chipset LPC/eSPI Controller +-1f.3 Intel Corporation Cannon Lake PCH cAVS +-1f.4 Intel Corporation Cannon Lake PCH SMBus Controller +-1f.5 Intel Corporation Cannon Lake PCH SPI Controller \-1f.6 Intel Corporation Ethernet Connection (7) I219-VYou need to be very careful running `axdevice --refresh`.I’ve got two machines that, by default, present the pci device tree in this way, and running `axdevice --refresh` triggered the NVMe drive to be disconnected from the system, resulting in filesystem corruption, which put the whole system into a read-only mode.It would be awesome if someone could update the axdevice script to only affect Axelera devices, and yes, this is a machine with the card installed, it just hasn’t been detected.

3
F
Ensign
Forum|Forum|6 months ago
F
Ensign
floritEnsign

LLM Models to be precompiledNew

r1-1776:70Bcodellamacodegemmathis models I want to usepost more models if you in LLM interested 

0
F
Ensign
Forum|Forum|6 months ago
F
Ensign
floritEnsign

eAIPUs for metis 4x quad core cardsNew

Simple view this cases https://amzn.eu/d/eUvVPBAyou can add some pcie 3.0/4.0 usb4/OCuLink Docks Like this:https://amzn.eu/d/avsiLCyOr this:https://amzn.eu/d/aotOmFnYou can add separate sfx power supply with a huge benefit forthe „PCIe metis 4x quad core accelarator 64GB“ you need a 450W power supplyto add the metis Card to a Minicomputer with usb4 40GB/s or OCuLinkV2 options with enough Power to work but a warning „This is expementerial“ My Build for this Action „minisforum ai x1 pro“ buyed with 50€ Off on https://minisforumpc.eu Shop with Code: AIX1PRO50 on checkout  

0
F
Ensign
Forum|Forum|7 months ago
T
Cadet
TimBCadet

Yocto Layer of voyager-sdkNew

A yocto-layer would greatly improve the possibility to add voyager-sdk to a wide range of projects.Currently, it takes a lot of manual work to implement everything to make it partly work with yocto.The install.sh script needs a lot of tweaking to be able to be executed on a target that does not have apt available. And also there is no official support of dkms for yocto yet. So a yocto-layer that fully installs every part of the voyager-sdk would be very nice.

1
Spanner
Forum|Forum|10 months ago
saadtiwana
Ensign
saadtiwanaEnsign

SDK example(s) on how to use detection models from OpenCVNew

The examples that come with the SDK mostly use pipelines that do all the work of getting the data from the source (files or usb camera), sending for inference, and then displaying the inference results on the images. This is great for many use cases, I am sure, and enable a high degree of efficiency. However, for many users, the AI inference is part of a C/C++/python application where the images are obtained via OpenCV, processed (scale/crop/etc) in opencv based on application logic, and then a part of the image is sent for AI detection. Once the result is obtained, then the application can display the results over the opencv image using it’s own custom logic.So in summary, it would be great to have some examples that demonstrate this process. A simple example that shows how to use a detection model from the model zoo in C or Python along with opencv for obtaining image and displaying the results. Another good example would be running the model inference as a gstreamer pipeline. This would allow developers to feed the images into it, and get the results out using tools they are already familiar with  (opencv, gstreamer, etc). p.s I am very new to Axlera/Metis so I apologize if I missed those examples :)

1
jaydeep.de
Forum|Forum|1 year ago
D
Cadet
doggenshozenCadet

LattePanda Sigma works with Metis M.2!New

Hi all! I wanted to contribute a little bit about my experience bringing up the Metis M.2 in my LattePanda Sigma. Im an EE who is self taught, I have worked for Harley Davidson, Span.io, Enel X NA, and I’ve done several consulting projects on synthesizers and drum machines. My interest in AI is hobby and curiosity based, not professional. Software engineering is a new skill Im creating.I first tried to run Metis on the Windows 11 operating system that came with LattePanda Sigma, and following the instructions on the git was extremely confusing. I have ADD, and some other learning differences, but that wasn’t the reason installing was so hard on Windows. It’s because there isn’t a single page with coherent instructions telling the user how to bring up the hardware in a simple step by step format. Having the user click between git pages on firmware, installation of drivers, wsl, putting Windows into test mode, using multiple programming environments, etc is painful and makes installing the hardware on Windows a miserable, confusing, and difficult experience.I’ll probably make my own step by step guide for Windows at some point since the instructions on git are confusing.I then tried to do the install on an old version of Ubuntu (support 24.04 please!) and I had much less trouble. I HIGHLY RECOMMEND using Ubuntu 22.04 to run the hardware and software over Windows. The instructions to install the Voyager-SDK on Ubuntu 22.04 actually worked pretty well. I was surprised.I ran into an issue at one point after installing the SDK: I couldn’t detect the Metis M.2 card. I couldn’t really figure out how to install the driver from the instructions for Ubuntu installation, so I had to download the .deb driver and install it similar to the “instructions for installing Voyager-SDK using Docker” to get the driver installed. Once the driver is installed, and the clunky SDK is installed and running, the demos with YOLO worked great, with the Metis M.2 card barely breaking a sweat doing inferences.

1
Spanner
Forum|Forum|1 year ago
F
Ensign
floritEnsign

we need more DRAM … from 1TB up to 4TBNew

Hello I got some Suggestion for the next Generation metis pcie x16 4.0 cardsWe Need more DRAM E.g. 1TB/2TB/4TBUp to 8x Quad Core processorsThis will be a good goal for Future cards

1
F
Ensign
Forum|Forum|1 year ago
T
Cadet
TheLinkedConnectionCadet

ai actors merged in video w/real actors?New

I'm developing a new way of video with or without AI. I am marketing both small & large companies using their people as limited actors. I saw Titanium and i was very curious, can I merge dynamic ai actors into video with real actors?  I am getting paperwork together to start, so I have time to learn. My background is in 2 & 3D animation & graphic design (degrees in both bs & bfa) What is the learning curve?  

1
Spanner
Forum|Forum|1 year ago
J
Axelera Team
JonasAxelera Team

🎥 Demo Drop: Multimodal segmentation and detection on Metis with Fast Segment AnythingUnder Consideration

This short video showcases an early experiment using the Voyager SDK and Metis AIPU to run Fast Segment Anything (FastSAM). It is based on YOLOv8-seg generating masks and CLIP to link the text prompt with visual masks in the video stream.What’s exciting is the flexibility—no need for retraining on specific classes. Just change the text prompt and it finds the object. This is still a test setup, but I thought it might spark a few ideas and show what’s becoming possible on the edge with Metis. Keen to hear what you guys think, or how you’d use this!

4
B
Forum|Forum|1 year ago
gurumeditation
Ensign
gurumeditationEnsign

Create new tagsUnder Consideration

Looks like tags are a thing on posts and questions, and there’s a tag cloud in the sidebar. I can select existing tags but can’t create new ones. If community members could add their own tags it could be a good way to categorize content going forward.

2
Axelera CMX
Forum|Forum|1 year ago
Dr Data
Ensign
Dr DataEnsign

A section for model testingNew

Can there be a section here in the community for testing models and providing feedback on which works, which don’t, what help is needed etc etc. Or to make requests for support of specific models. Either one and the same or two different areas really.

0
Dr Data
Ensign
Forum|Forum|1 year ago
Code of ConductAccessibility statement

Address

HTC5, High Tech Campus
5656 AE Eindhoven
The Netherlands
Email: info@axelera.ai

Follow us: LinkedIn X YouTube

Menu

AI Accelerators

AI Software

Metis Systems

Partners

Product Inquiry

Expert Review Program

Company

Our Story

Our Team

Careers

News

Contact

Sign Up For Our Newsletter

EU flag Axelera® AI is co-funded by the European Union’s Horizon research and innovation programme.

Privacy Policy  |  Cookie Policy  |  Sales Terms & Conditions  |  Vulnerability Disclosure Policy  |  End-User License Agreement

Copyright © 2026, Axelera AI B.V.