Metis M.2

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

(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

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

HI ,I have an RK3588 board running Debian, and I would like to use it with an Axelera M.2 AI card. However, I cannot find any related installation or porting documentation.Does anyone have experience with this?Thank you.

Hi again, long time to see ^^After 6 months I saw a post about ORIN support and I wanted to try my Metis M.2 again.First I wanted to try it on my Desktop computer, ORIN will come after. But unfortunately, I got some errors.Note: I was able to run Metis M.2 on my desktop before.Now I am using same operating system (Ubuntu 22.04) but with different kernel version I suppose.I can install the repo succesfully but when I try to run “axdevice” command it gives me an error like this:[libdmabuf.c:1712] Device communication timed out: device did not respond within 1 seconds. (0)WARNING:axelera.runtime:Failed to get valid board type for device metis-0:2:0 got 5Device 0: metis-0:2:0 board_type=unknown (not responding)What I try to solve problem but didnt help:Disabled secure boot from BIOS Disabled Intel_iommu from grub entry Disabled pcie_aspm from grub entr

I am looking for a way to infer Qwen VL 32b instruct A3b on the edge using Axelera m 2 form factor hardware. But I would need a lot of Ram to make this happen I am talking at least 48Gb. Could anyone share some light on what are my options. I need to do video inferencing and scene understanding on request from the user. My idea was to grab a few frames whenever the request was initiated and then choose the best frame to do inference. 

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 SSD PIP PCIe Peripheral Board with the external power connector but am concerned about current flowing back into the RPI 5 through the PCIe cable.I tried powering both the RPI 5 and Metis M2 board by applying 5V with a 5A limit (5A being the limit of my bench supply) to the 5V GPIO connector pin but the RPI 5 did not boot correctly. I suspect it’s an issue with the inrush current demands of the RPI 5 and Metis M2 together exceeding 5A.Thank you for your help!

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 prevented the firmware from being updated.Host: Raspberry Pi 5OS: Raspberry Pi OS (Debian-based)Kernel: 6.12.47+rpt-rpi-2712Driver: metis 1.2.4SDK: 1.4.2Flash firmware: 1.3.2Issue: Device communication timeout (1 second) during firmware operationsPCIe: x1 link (Pi 5 M.2 limitation)Error: DMABUF_METIS_XFER failed, UnsupReq PCIe errorsDo you have any advice on how to proceed?

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 Sam

HI, We ran axdevice --report on M.2-aipu to check the number of active cores. The output shows “Device metis-0:2:0”.Does this string confirm that only two cores are available? We had expected four cores (e.g., a notation like “metis-0:4:0”). We want to know from this log whether the hardware is limited to two cores. Best, regardsHiroyuki Kojima

Hi,I'm having trouble installing the metis-dkms driver. Can you help me?The device is a NanoPC-T6 from Friendly Elec, and the operating system is Ubuntu 22.04, also provided by Friendly Elec.I'm leaving the error message and OS information below. If there is any more information I should provide, please let me know. Thank you. The Error:$ sudo dpkg -i metis-dkms_0.07.16_all.deb(Reading database ... 155441 files and directories currently installed.)Preparing to unpack metis-dkms_0.07.16_all.deb ...Deleting module metis-0.07.16 completely from the DKMS tree.Unpacking metis-dkms (0.07.16) over (0.07.16) ...Setting up metis-dkms (0.07.16) ...Loading new m

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 :)

Non c’è modo di aggiungere RAM a questa bellezza 😁?E’ perfetta per il mio Laptop o su Orange PI ( Embedded ).PCIe 5.0 ? LLM non gira su M.2 ? 😣Leggendo l’SDK… Interessante… 🤔

I wanna use axelera metis on alinx board and I wonder that is there any yocto support? 

Hello,My team just received and opened a Metis Dev System with Arduino Portenta X8.We followed the “Getting Started with Metis Dev System with Arduino Portenta X8”,but could not go though; In installing the SDK;          “docker run -it --privileged -v /tmp:/tmp -v /axelera:/axelera -v /lib/modules:/lib/modules -v /run:/run -v /dev:/dev --group-add video -e DISPLAY=$DISPLAY --name=voyager-sdk-1.4.0 --network=host --entrypoint=/bin/bash axelera-sdk-ubuntu-2204-arm64-prebuid-llm:1.4.0”    failed with           “docker: Error response from daemon: pull access denied for axelera-sdk-ubuntu-2204-arm64-prebuild-llm, repository does not exist or may require ‘docketr login’: denied: requested access to the resource is denied” message          What is the default login ID/PASS of the docker image ?    2. Then, we tried the alternative ; after loading the downloaded docker image,          w

Hi guys, new to the conversation here.Just wondering whether there is a software compatibility matrix available somewhere?I’ve been trying to get the METIS M2 chip running on my Jetson Orin NX. Thing is, I’m running a custom YOCTO build (based on Jetpack 6) and want to run the voyager-sdk in a Docker container, but I just can’t seem to get the drivers to properly match. So what driver versions match with which voyager-sdk versions?The main error I’m getting is the one below:root@hw00001aaa-24050002:/workspace# axdevice --pcie-scan0007:01:00.0 : Axelera AI Metis AIPU (rev 02)[libtriton_linux.c:799] Failed to open '/dev/metis-7:1:0': No such device[AxeleraDevice.cpp:71] Device not found: metis-7:1:0WARNING: Failed to open device 0(metis-7:1:0)[libtriton_linux.c:799] Failed to open '/dev/metis-7:1:0': No such device[AxeleraDevice.cpp:71] Device not found: metis-7:1:0ERROR: Failed to open device metis-7:1:

Hello,I’m running inference with model  unet_fcn_512-cityscapes with pipe torch-aipu on the aetina eval board. It runs at 1.8 fps system and with 500ms of latency although device fps shows  11.5 fps capability. In the doc it is also mentioned that it should reach 18fps. I originally thought it was an issue with time wasted to load and decode png images from the SD card so I put them in shared memory but result are identical.I also tested yolov5s-v7-coco that should reach 805 fps but I can only achieve 214fps. Here are the output of: AXELERA_USE_CL_DOUBLE_BUFFER=0 ./inference.py yolov5s-v7-coco media/traffic3_720p.mp4 --show-stats --no-displayINFO : Deploying model yolov5s-v7-coco for 4 cores. This may take a while...|████████████████████████████████████████| 12:41.1 arm_release_ver: g13p0-01eac0, rk_so_ver: 9========================================================================

Hello guys;I did not follow the instructions in the link below on the Orangepi 5 device, but it does not see the device.“ERR DEVCICE NOT FOUND”help! https://support.axelera.ai/hc/en-us/articles/27059519168146-Bring-up-Voyager-SDK-in-Orange-Pi-5-Plus

Hi there,i´m working with an Axelera M.2 chip at uni. For some research on green AI i´m doing i want to track the power usage of the chip. As far as i know i need to track the power through the PCIe connection. Is there a way to track it with the AIPU directly or do i need to use the PCIe? And if there is a way can i save the usage in an array easily or is this a rather tricky situation?Thanks in advance Morruebe

Will Metis M.2 ( AXE-BME20M1AR01B02) work with QNAP NAS?

Hello everyone!I am Luca Gessi, from Italy. I am a (lucky) owner of Aetina board with M2 Axelera Metis. Unfortunatly the board arrived without the SDK installed. I installed it using the github guide. The procedure faced several issues and broken packages. I had to run it several time but at the end the installation completed.From this I tried to run simple command for testing the board (as suggested on the getting started guide):./inference.py --no-display yolov5s-v7-coco dataset However the inference failed: (venv) aetina@aetina:~/voyager-sdk$ ./inference.py --no-display yolov5s-v7-coco datasetERROR   : timeout for querying an inferencearm_release_ver: g13p0-01eac0, rk_so_ver: 9INFO    : Using dataset valINFO    : Dataset 'COCO2017' split 'val' downloaded successfully to /home/aetina/.cache/axelera/data/cocoINFO    : Dataset 'COCO2017' split 'labels' downl

I'm evaluating your devices. I really love both the European heart and the great TOPS/Watt ratio.It would be amazing for edge computing.On the other side, our company is waiting for a GX10 from ASUS/NVidia with 128Gb of shared memory.The reason why I think that the Metis form factor is more interesting than the pci-ex would need a very long document :-)I read that your SDK is supporting off-load but reading on the forum I think that your off-loading support is limited only to data and not the core of the model.You know that when you use CUDA+torch you're able to off-load some part of the model out of the GPU memory and execute it running a small part of the model at once swapping coefficients from the GPU memory to the host RAM and vice versa.Are you planning to improve your off-loading system in your SDK?Are you planning to introduce a Metis with more RAM? 

Hi ​@emustafa, please I need some helpI tried to upgrade firmware of Metis M2 but system (metis installed on orangepi 5 plus) gave me some errors and now after a few of reboots I obtain always same bad response from axdevice: libtriton_linux.c:1082] Device communication timed out: device did not respond within 1 seconds. (0)WARNING: Failed to get valid board type for device metis-0:1:0 got 6Device 0: metis-0:1:0 board_type=unknown (not responding) have I some possibilities to recover it? can I run some tools to diagnose bettere situation?thank in advance

I’ve read a number of posts and am not sure. I have a Minisforum um890 pro with Ryzen 9 8845s and 64gb ram. Windows. I’m experimenting with various hardware and setup and am wondering if this would help inference speed if used in my M.2 slot. I have USB4 and Oculink ports so I could use an external PCIe adapter. Is it plug n play or do I need to use the SDK to configure it? TIA!

I am using the Metis M.2 Card on my host PC. It is detected using `lspci` and `axdevice`. I am able to run inference using `./inference.py yolov5m-v7-coco-tracker usb:0`. However when I try to use the AxRuntime API (Python) I get the following: from axelera.runtime import Context,context = Context()model_path = "/home/user/axelera/testing/data/yolov5/compile/compiled_model/model.json"model = context.load_model(model_path)batch_size = 1connection = context.device_connect(None, batch_size)instance = connection.load_model_instance(model, num_sub_devices=batch_size, aipu_cores=batch_size)[ERROR][axeDeviceMemoryAllocate]: Not enough memory: free memory 1531904, request memory 16520704.[ERROR][axeDeviceMemAlloc]: Device memory allocate failed: size 16520704.[ERROR][axeMemAllocDevice]: Device memory allocate failed: 0x70010001.Error at zeMemAllocDevice(context, &