Metis M.2

I recently acquired a Metis M.2 module and was so excited to get started with it. To my horror, I installed it into a standard, modern x86 mini PC (with power disconnected, all by the books), and the system was bricked upon my first attempt to boot. At first, I thought maybe the M.2 slot on the system was not providing adequate power for the device, and to the benefit of the Metis, I decided to try another host system. HUGE mistake. The same thing happened with a LattePanda x86 SBC, confirmed to have enough power to the M-key M.2 slot. These systems are not cheap, so to say I am disappointed is an incredible understatement.  Maybe I’m just not understanding where to look for host system specs, but it doesn’t seem like this issue is warned against anywhere in your docs or on the community page here. Has anyone else had this problem? I’m down two systems, so if someone could please tell me with certainty which system I CAN reliably plug this thing into, I would be very appreciative. EDIT

As the title suggests, I want to factory reset the board so that I can reinstall and setup the board from a clean state? How can I do it?

Will this ever be made available? I am interested in the 16gb version.   

Hey everyone,I am evaluating the Metis lineup for an edge AI project and have a specific question about multi-card architecture that I haven't found a definitive answer to in the docs or SDK references.What I understand is supported today: The Voyager SDK detects multiple Metis cards in a single host. Each card runs its own independent inference pipeline. A real-world surveillance example shows three 4-chip PCIe cards running five primary models + one secondary model in parallel across 48 AIPU cores. My question: Is there any current or planned SDK support for splitting a single neural network across multiple Metis cards (e.g., layer sharding or tensor parallelism across two M.2 cards)? Or is the architecture strictly "one model must fit entirely within a single card's memory and AIPU"?Context for my use case: I am looking at a host with dual M.2 slots (e.g., Radxa Orion O6N) and weighing whether two standard Metis M.2 cards could act as a unified 2-GB / 428-TOPS accelerator for a

Hi, when running inference on Metis M.2 on raspberry CM5 we noticed these errors occuring after couple minutes. error log: [libtriton_linux.c:531] DMABUF_METIS_XFER failed: Input/output error [AxeleraDmaBuf.cpp:222] DMA transfer failed: Input/output error [ERROR][axeShareMemoryExecute]: Dmabuf transfer failed. [ERROR][axeCommandQueueExecuteCommandListsAsync]: Level-zero memory operation failed: 0x70010001. terminate called after throwing an instance of 'std::runtime_error' what():  axr_run_model failed with Error at zeCommandQueueExecuteCommandLists(cmdqueue, n_cmdlists, cmdlists, nullptr): cmdqueue_run_cmdlists: 319: Exit with error code: 0x70010001 : ZE_RESULT_ERROR_NOT_AVAILABLE kernel errror log: axl 0001:01:00.0: DMA error WR CH0 (ctrl 0x1) setup:  Runtime: runtime-1.5.3-1 - Voyager SDK: v1.5.2 - metis-dkms: 1.4.4 - Firmware: flash version 1.5.0 - bcver 7.1

Hi! My name is Salvador and I’ve been trying to integrate the Metis M.2 on a Jetson Orin NX 16GB to perform Computer vision tasks.Recently the Axelera team shared a guide to Bring up Metis M.2 on Jetson Orin, where they explain the steps required to modify the kernel to use the Metis Accelerator.For me these changes were not enough, so I had to perform additional steps to make it work, I hope this post is useful for anybody trying to accomplish the same. The following steps build upon the instructions provided by the Axelera team.Prepare the Nvidia files necessaryWe will use a host machine running Ubuntu 20.04 or 22.04 (newer versions are not compatible with some Nvidia tools) where we will run all the described process, download the kernel sources, the Jetson Sample Filesystem, and the Jetson linux toolchain, and execute the cross compilation of the linux kernel, and the flashing into the Jetson Oring NX. To install the Jetson toolchain just follow the instructions provided on the lin

Hello, i just got my m.2 card and on my AMD64 desktop workstation, the Metis M.2 AIPU does not survive an S3(suspend-to-RAM) cycle. After resume, every large DMA transfer to the cardfails permanently. Only a full cold power-cycle restores function — a warmreboot is not enough. This makes the card unusable on any normal desktop,where suspend/resume is the standard daily workflow.I narrowed this down together with Claude Opus 4.8 (Anthropic) over a detaileddebugging session. Full diagnosis below.## Hardware / Software- Host: AMD Ryzen, B850 platform, RTX 3090 in primary slot- OS: CachyOS (Arch-based), kernel 7.0.12 (Clang/LLVM-built), Secure Boot off- Metis M.2 AIPU, PCIe 0000:0c:00.0 (1f9d:1100 rev 02), Gen3 x4- Driver: axelera-driver release/v1.6 (module version 1.4.17), built with  make LLVM=1, DKMS-managed- SDK: Voyager 1.6.1 (axelera-rt / devkit), inference via distrobox/Ubuntu 24.04## Reproduction1. Cold boot. Run inference (yolo26s-coco-onnx, fakevideo) → works, ~529 fps.2. system

use the metis m.2, zed x and nvme on a jetson orin nx 16gb a condensed field guide to a real-time vision stack on the orin nx 16gb: preempt_rt kernel, axelera metis npu, zed x stereo, nvme. every section here exists in long form in the repository docs, linked throughout and listed at the end. what this isa complete recipe for taking a stock jetson orin nx 16gb and turning it into a real-time vision platform:custom preempt_rt kernel with low-jitter tuning (cyclictest avg ~3 µs on the isolated cores; max under the 100 µs gate make verify enforces. run it headless — a desktop session adds ~150 µs ipi spikes) axelera metis m.2 as the inference accelerator (in-tree driver, not oot, vermagic-safe). detection costs the jetson's gpu essentially nothing, which is the whole point stereolabs zed x via the zed link mono capture card (max9296 deserializer) nvme boot + a btrfs data partition for recordings dmabuf zero-copy pipeline (design goal: camera → isp → npu with no cpu memcpy)everything below

Hello.I recently received the m.2 metis accelerators and did a test on the boards provided by Axelera and got results close to the published benchmarks. It was succesful.I then connected these accelerators to the Orin (via the m.2 slot) in order to use them also for the my Jetson AGX Orin environment. But in the voyager-sdk installation i got “WARNING: Failed to refresh pcie and firmware” error. The installation completes but the accelerator device does not show up on my system. In lspci -tv command I get the output attached to this post. Can’t see metis there.I didn't see any information about the compatibility of these accelerators with Jetson systems (my m2 slot is M-key). If they are compatible, can you help me to fix the installation?Thanks :)

Hello,There seems to be two different published benchmarks for ResNet50.The first is in the Voyager SDK’s documentation : 1756 FPS (M.2) / 1946 FPS (PCIe) :- https://github.com/axelera-ai-hub/voyager-sdk/blob/latest/docs/reference/model_zoo.mdThe second is on the Metis Marketing page : Up to 3200 frames per second (ResNet-50)- https://axelera.ai/ai-accelerators/aipu/metis I was able to achieve 2050 FPS, which is higher than the modelzoo documentation, but MUCH lower than the marketing claim:- https://mariobergeron.com/posts/edge-ai-power-p04-axelera-metis/ Where does the 3200 FPS benchmark claim come from ?   How was this benchmark achieved on Metis ?  Which hardware platform ?Which brings me to the next marketing claim : Industry-Leading FPS / Watt ratios on ResNet50v1 (graph showing 614 FPS/W- https://axelera.ai/ai-accelerators/aipu/metis I was only able to achieve 270 FPS/W :- https://mariobergeron.com/posts/edge-ai-power-p04-axelera-metis/ What does the 614 FPS/W benchmark come fro

How can I deploy WASB model on metis m2?

Hello Axelera support team,I am running the Axelera Metis M.2 accelerator on a Radxa Rock 5B (RK3588 SoC) with Armbian and kernel 6.18.10-current-rockchip64. After extensive debugging over several days, I have identified a compatibility issue between the metis driver and the ARM SMMU-v3 on this platform. I would appreciate your guidance on resolving this.HARDWARE & SOFTWAREBoard: Radxa Rock 5B (RK3588, 8GB RAM, PCIE3.0-4X) OS: Armbian, kernel 6.18.10-current-rockchip64 (mainline) Accelerator: Axelera Metis M.2 Driver version: metis 1.4.16 SDK/Runtime version: voyager-sdk / runtime-1.6.0-1 PSU: 65WWHAT WORKSThe Metis is detected correctly via PCIe: lspci shows "Axelera AI Metis AIPU (rev 02)" at 0000:01:00.0 After patching the Device Tree to expand the PCIe memory window (the default 14MB window was too small; expanded the 64-bit prefetchable range at 0x900000000 to 128MB), the driver loads successfully: /dev/metis0 -> metis-0:1:0 is created "Axelera AIPU PCIe Driver, version 1.

I would like to use the Metis M.2 in an embedded system running Open Embedded with a 4.19 kernel. (It doesn’t have the “modern” /dev/dma_heap/ interface, it uses /dev/ion). I have the driver installed in the host, and when I use the SDK in a Ubuntu 22.04 docker container I get this error:[libaxldev_linux.c:394] No dmabuf driver found[ERROR][axeShareMemAllocMap]: Fail to alloc dmabuf[ERROR][axeMemAllocShared]: Share memory allocate mao failed: 0x70010001.terminate called after throwing an instance of 'std::runtime_error'  what():  axr_load_model_instance failed : Failed to create executor for model: kernel_function_batchedAborted Can the driver/library be compiled to use ION instead of dmabuf?

Title says it all -- any timeline for a “wrynose” release for the M.2 card so it can be included in a wrynose Yocto Project build?

I'm trying to do a pci passthrough from proxmox to my VM.I keep getting the error when starting my VM. error writing '1' to '/sys/bus/pci/devices/0000:02:00.0/reset': Inappropriate ioctl for devicefailed to reset PCI device '0000:02:00.0', but trying to continue as not all devices need a resetkvm: ../hw/pci/pci.c:1815: pci_irq_handler: Assertion `0 <= irq_num && irq_num < PCI_NUM_PINS' failed.TASK ERROR: start failed: QEMU exited with code 1This is my machine details agent: 1bios: ovmfboot: order=scsi0;ide2;net0cores: 4cpu: x86-64-v2-AESefidisk0: local-lvm:vm-103-disk-0,efitype=4m,ms-cert=2023,pre-enrolled-keys=1,size=4Mhostpci0: 0000:02:00.0,pcie=1,rombar=1ide2: none,media=cdrommachine: q35memory: 4096meta: creation-qemu=10.1.2,ctime=1776892906name: axeleranet0: virtio=BC:24:11:A4:8C:9B,bridge=vmbr0,firewall=1numa: 0ostype: l26scsi0: local-lvm:vm-103-disk-1,iothread=1,size=32Gscsihw: virtio-scsi-singlesmbios1: uuid=49dcbf39-39e5-4a39-a8ad-cc02f5c886bfsockets: 1vmgenid: 9

I just got a Metis M.2 card, and and having problems getting it to show up correctly as a PCI device. During boot, the vendor and device ID are detected as [16c3:abcd], which is for a generic Synopsis PCIe bridge. Is this correct? During boot, I am also getting an error “dwc3-haps 0002:01:00.0: failed to enable pci device”After boot, the Metis M.2, as well as the root port it is connected to are uninitialized and return 0xFFFF for all configuration space. I’m not sure if that is a symptom, or a result of the previous error.The host machine is our own edge device based on a Qualcomm QRB5165 processor, running OE Linux with a 4.19 kernel. The M.2 slot currently provides a Gen 3 x1 PCIe connection.I tried increasing the time between reset de-assertion to configuration to 500ms in case the card needed more time, but that didn’t help. I have also monitored the 3.3V supplying the M.2 slot to make sure the voltage didn’t drop.We have used this M.2 slot for other cards, e.g. NVMe without a pro

I’m running the metis m.2 chip in a micro pc and the temps are quite high when running the inference.Core Temp is showing 110.0°C.What can we do to lower these temps, or is it fine?Thanks

I am trying to run some filtering models for my workflow on Axelera Metis. However, the `axcompile` command doesn’t allow for inputs with batch size (dim = 0) to be greater than 1. During model inference, that means that I have to pass inputs in a sequential order which introduces latency. The model is a custom model (not in model zoo) and not a vision model. I have tried creating 4 instances of the same model running on each of the cores of Metis AIPU, but that isn’t possible due to SRAM memory limitations. Is there a way to use Batch Size > 1 for Metis? 

Dear Axelera Support, I am attempting to install Voyager SDK on the radxa rock 5T board with the axelera AI Accelerator M.2. While the SDK suggests using Ubuntu 22.04, I could not find a version of ubuntu for the 5T (https://github.com/DHDAXCW/ubuntu-rockchip-rk3588?tab=readme-ov-file)  I have reviewed previous threads but either they’re not fixed (https://community.axelera.ai/support-central-47/subject-metis-aipu-detected-on-pcie-but-not-responding-stage0-load-failure-on-rk3588-compute-board-voyager-sdk-1-5-3-1280) or there’s an ubuntu version available (https://community.axelera.ai/metis-pcie-7/pcie-connection-doesn-t-work-with-radxa-rock-5b-1101)  I’m not exactly sure if I can use the ubuntu image meant for the Radxa Rock 5B+ on the Rock 5T? radxa@rock-5t:~$ cat /etc/os-releasePRETTY_NAME="Debian GNU/Linux 12 (bookworm)"NAME="Debian GNU/Linux"VERSION_ID="12"VERSION="12 (bookworm)"VERSION_CODENAME=bookwormID=debian radxa@rock-5t:~$ cat /sys/class/metis/version1.4.16 Installation of S

Hello Axelera support team,I am running the Axelera Metis M.2 accelerator on a Radxa Rock 5B (RK3588 SoC) with Armbian and kernel 6.18.10-current-rockchip64. After extensive debugging over several days, I have identified a compatibility issue between the metis driver and the ARM SMMU-v3 on this platform. I would appreciate your guidance on resolving this.HARDWARE & SOFTWAREBoard: Radxa Rock 5B (RK3588, 8GB RAM, PCIE3.0-X4) not 5B+ model. OS: Armbian, kernel 6.18.10-current-rockchip64 (mainline) Accelerator: Axelera Metis M.2 Driver version: metis 1.4.16 SDK/Runtime version: voyager-sdk / runtime-1.6.0-1 PSU: 65WWHAT WORKSThe Metis is detected correctly via PCIe: lspci shows "Axelera AI Metis AIPU (rev 02)" at 0000:01:00.0 After patching the Device Tree to expand the PCIe memory window (the default 14MB window was too small; expanded the 64-bit prefetchable range at 0x900000000 to 128MB), the driver loads successfully: /dev/metis0 -> metis-0:1:0 is created "Axelera AIPU PCIe Dri

 Hi,I'm trying to install a Metis AI Accelerator M.2 Card using the Voyager SDK install.sh script. I successfully installed the card on my setup.Current environment: Debian 12 with a custom kernel Motherboard: Advantech SOM-DB5920 x4 PCIe to M.2 PCIe Adapter (StarTech.com) The Metis card is correctly detected through the PCIe adapter:lspci | grep Metis02:00.0 Processing accelerators: Axelera AI Metis AIPU (rev 02)When i verify the installation using axdevice command i have this issue: axdevice -v INFO: Found PCI device: 02:00.0 Processing accelerators: Axelera AI Metis AIPU (rev 02)INFO: Found AIPU driver: metis                 110592  0[libtriton_linux.c:1313] Device communication timed out: device did not respond within 1 seconds. (4294967295)WARNING: Failed to get valid board type for device metis-0:2:0 got 8INFO: Ignoring device 0(metis-0:2:0) as it has not returned a valid board type: 8INFO: Using device metis-0:2:0Device 0: metis-0:2:0 board_type=unknown (not responding) I fo

I am using Radxa Rock 5B (RK3588, 8GB RAM) board along with Metis M.2 accelerator. I have successfully done the initial troubleshooting for the RK3588 during installation (memory expansion in dts, etc.) and installed the driver. However, the Metis board is not working as expected. The board is detected during lspci scan:reck@reck:~$ lspci0000:00:00.0 PCI bridge: Rockchip Electronics Co., Ltd RK3588 (rev 01)0000:01:00.0 Processing accelerators: Axelera AI Metis AIPU (rev 02)0002:20:00.0 PCI bridge: Rockchip Electronics Co., Ltd RK3588 (rev 01)0002:21:00.0 Network controller: Realtek Semiconductor Co., Ltd. RTL8852BE PCIe 802.11ax Wireless Network Controller0004:40:00.0 PCI bridge: Rockchip Electronics Co., Ltd RK3588 (rev 01)0004:41:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8125 2.5GbE Controller (rev 05)reck@reck:~$ lspci -s 0000:01:00.0 -vv 0000:01:00.0 Processing accelerators: Axelera AI Metis AIPU (rev 02) Subsystem: Axelera AI Metis AIPU (rev 02) Control: I/O- Me

https://github.com/Lonewolf-Information-systems/CM5-Exaviz/blob/main/Arch-Linux/metis-dkms/PKGBUILD https://github.com/Lonewolf-Information-systems/CM5-Exaviz/blob/main/Arch-Linux/metis-sdk/PKGBUILD https://github.com/Lonewolf-Information-systems/CM5-Exaviz/tree/main/axelera.ai-overlay gentoo related...

Dear Team,I am currently trying to deploy a model that takes two input images as input. I get around that I have made changes to my model(OpticalFlow based Model) and it now takes (1,6,H,W). I have written a custom DataAdapter which makes sure that the input is concatenation of two images. I am getting following error when deploying ERROR :axelera.runtime: Expecting 2/1 input/output arguments, but got 1/1 instead.ERROR :axelera.app.pipe.torch: Pipeline error occurred: AXR_ERROR_INVALID_ARGUMENT: Expecting 2/1 input/output arguments, but got 1/1 instead.ERROR :axelera.app.pipe.torch: Traceback (most recent call last):ERROR :axelera.app.pipe.torch: File "/root/voyager-sdk/axelera/app/pipe/torch.py", line 52, in _loopERROR :axelera.app.pipe.torch: image, result, meta = model_pipe.inference.exec_torch(ERROR :axelera.app.pipe.torch: File "/root/voyager-sdk/axelera/app/operators/inference.py", line 1017, in exec_torchERROR :axelera.app.pipe.torch: self._axr_modeli.r

(venv) smart@smart-Default-string:~/voyager-sdk$ axdeviceERROR: No target device found in lspci outputERROR: AXR_ERROR_CONNECTION_ERROR: No target device found in lspci output(venv) smart@smart-Default-string:~/voyager-sdk$ axdevice --refresh[sudo] password for smart: ERROR: No target device found in lspci outputERROR: AXR_ERROR_CONNECTION_ERROR: No target device found in lspci output(venv) smart@smart-Default-string:~/voyager-sdk$ axdevice --refresh -vINFO: No Axelera devices found, will only rescan.INFO: PCIE rescanERROR: No target device found in lspci outputTraceback (most recent call last): File "/home/smart/.cache/axelera/venvs/644f17ff/bin/axdevice", line 8, in <module> sys.exit(entrypoint_main()) ^^^^^^^^^^^^^^^^^ File "/home/smart/.cache/axelera/venvs/644f17ff/lib/python3.12/site-packages/axelera/runtime/axdevice.py", line 794, in entrypoint_main main(args) File "/home/smart/.cache/axelera/venvs/644f17ff/lib/python3.12/site-packages/axelera/runtime/a