Skip to main content

Unanswered questions

20
G
Cadet
GiodstCadet
 Voyager SDK
Yolo11-coco-onnx of the model zoo low performance

Hi,I tried the Yolo11-coco-onnx models from Model Zoo and got terrible results. Can anyone give me some advice? ./inference.py yolo11n-coco-onnx dataset --no-display --show-device-fpsINFO    : Model:      yolo11n-coco-onnx                                         INFO    : Dataset:    CocoDataset-COCO2017INFO    : Date:       2025-08-21 12:33:18.028455INFO    : Inference Time: 67178.89msINFO    : Evaluation Time: 36222.56msINFO    : Evaluation Metrics:INFO    : =========================INFO    : | mAP_box       | 0.03% |INFO    : | mAP50_box     | 0.05% |INFO    : | precision_box | 0.08% |INFO    : | recall_box    | 1.70% |INFO    : =========================INFO    : Key Metric (mAP_box): 0.03%INFO    : Core Temp : 49.0°C                                                    INFO    : Metis : 804.0fpsINFO    : CPU % : 31.4%INFO    : End-to-end : 74.7fps./inference.py yolo11s-coco-onnx dataset --no-display --show-device-fpsINFO    : Model:      yolo11s-coco-onnx                            

725
H
Axelera Team
L
Cadet
LindeCadet
 Voyager SDK
Is there some low level NumPy / ONNX example?

I’m doing some testing with the PCI-Express based AI card. After some initial hiccups due to motherboard compatibility which required me to swap place for GPU and AI-card and then exposing the card into a ubuntu-22.04 docker container it’s working fine. I’m impressed by the performance of the card compared to using --pipe torch and having a CUDA based backend for the benchmark problems identifying traffic. I want to do inference with not only custom weights, but also custom nets and see how it performs. My wish is to have a sample that uses numpy f32 arrays as input and output and does inference on the card given a model from a ONNX file. To keep it simple, I made a PyTorch net [3, 64][ Relu ][64, 64][ Relu ][64, 1] and trained iton a mathematical function f(x1, x2, x3) = y.This toy net was exported to ONNX. From there I wanted to test inference on the AI card before moving to more complex things.I could not see that my wanted usecase was compatible with `deploy.py` and the required it

251
L
Cadet
D
Cadet
dario.finardiCadet
 Metis M.2
M.2 with more RAM or a smarter off-load

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? 

160
D
Cadet
A
Cadet
alsuttonCadet
 Metis PCIe
Power requirements and PCIe slots

I’m putting an idea out to see if anyone has some data to back a theory.I’ve been talking with ​@Spanner about some problems I was having with a card, and, after looking over everything I’ve done, I’m wondering if a 75W slot is *required* rather than recommended, which would mean you need to use a PCIe x16 slot.One issue I had with the card was a small v shaped cut-out in the full height PCIe back-plate, which meant that the card wouldn’t sit fully into any PCIe x16 slot that I had (photo attached so you can see what I mean). This meant I had to use a 8x or 4x slot.Looking through the PCIe spec, only 16x slots are supplied with 75W, meaning that the 8x and 4x slots I tried were limited to 25W (which I confirmed), which I’m thinking could be the cause of the problems I saw.I have a 2nd hand machine turning up next week which I can test this theory on more easily (eBay still is useful for some things), but I’m wondering whether the PCIe card should be sized for a 16x slot in order to ens

572
A
Cadet
lorenzo.lamberti
Cadet
lorenzo.lambertiCadet
 Voyager SDK
Firefly ITX-3588J : i can not load the metis board not detected

Hello everyone, I am trying to use the Metis PCIe (4GB) in combination with the firefly ITX-3588J.Issue: I can not load the Metis kernel module (driver) into the Linux kernelSetup: I have the Metis PCIe with 4GB of ram  the Firefly ITX-3588J with 16GB of ram with a RockChip. OS: Ubuntu 22.04.4 LTS. I have a Gen3 Pcie with 4 lanes, details below```        LnkCap:    Port #0, Speed 8GT/s, Width x4, ASPM L0s L1, Exit Latency L0s <4us, L1 <16us            ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp+``` So far:I installed the ubuntu OS as described here: https://support.axelera.ai/hc/en-us/articles/25556437653138-System-Imaging-Guide-Firefly-RK3588 I installed the latest 1.3.3 voyager sdk release.  i can see the metis board from lspci``` firefly@firefly:~$ lspci | grep accelerators01:00.0 Processing accelerators: Axelera AI Metis AIPU (rev 02)```however, i do not detect any drivers for the board, even after installing the sdk. Both the following commands do not return anything:```

262
Spanner
Axelera Team
M
Cadet
MehmetYigitCadet
 Metis M.2
Metis M.2 Accelerator Can't Recognized by Jetson AGX Orin

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 :)

22411
Spanner
Axelera Team
P
Cadet
PepijnCadet
 Metis PCIe
deploy.py takes really long yolov8 model

Hi, I’m trying to deploy and inference with a yolov8 segmentation model. I tried to follow the tutorial, but I just get:INFO: deploying model yolov8sseg-coco for 4 cores. This may take a while… How long should this run? I left it on for 3.5 hours and nothing happened (except the loading bar). This seems to be a model included in your library: yolov8sseg-coco.Any idea if I can turn on more extensive logging to see what is happening? Thank you in advance!  

9615
Spanner
Axelera Team
llrds
Ensign
llrdsEnsign
 Project Challenge: Recognize & React
How to solve "ModuleNotFoundError: No module named 'axelera.app'"

When trying to run the application.py example, I get this error. The vent is activated. Per this thread I thought I could solve with a removal of the venv and reinstall but it’s being persistent now. Has anybody else found and overcome this?I’m using the Aetina Eval Board that came with the Project challenge kit.

655
A
Axelera Team
H
Cadet
HermioneCadet
 Voyager SDK
inference.py quick start - import Gst failed ModuleNotFoundError

Hi,My goal is to try out a few tutorials with the latest SDK release. Looks like a python package is not found, any clues what I could try?System: Axelere M.2 Card with Aetina Eval SystemVoyager SDK v1.3.1 - a fresh install of the SDK this timeFirst installed the latest driver https://software.axelera.ai/artifactory/axelera-apt-source/metis-dkms/metis-dkms_1.0.2_all.debthen I ran the installer with./install.sh --all --media --user <email addr> --token <token>I got a few suspicious warnings and hit ‘y’ a number of times. Then install of 186 packages completed.[185/186] Install gstreamer1.0-rtspbuilding operatorsrefreshing pcie and firmware0000:01:00.0 : DeviceDevice 0: metis-0:1:0 1GiB m2 flver=1.2.0-rc2 bcver=1.0 clock=800MHz(0-3:800MHz) mvm=0-3:100%Installation complete, but with unresolved issues (see above) firefly@aetina:~/Documents/g2-testing/voyager-sdk$ source venv/bin/activate I proceeded to try inference.py with one of the included videos as input(venv) firefly@aet

806
M
llrds
Ensign
llrdsEnsign
 Project Challenge: Recognize & React
Can we control the fan speed on Aetina RK3588?

I have SDK Version 1.3.3, there is a comment in release notes about fan but it seems to be for the Metis. I saw already threads discussing the PCIe and M.2 fan speed on the Metis, this question is about the Aetina evalkit running at 100% fan all the time.There are none of these types of details in here.https://support.axelera.ai/hc/en-us/articles/22846665291794-AETINA-RK3588-Industrial-Motherboard-M-2I tried wider searching Aetina and Firefly on Google, there are some suggestion that control might be possible in /sys/class/hwmon but I could not find a match, or I should be looking for something else in there.Can I make the fan speed of the SBC by dynamic?

1589
llrds
Ensign
S
Cadet
SiegfriedCadet
 Voyager SDK
uv build

Hi,I was wondering if there exist an astral uv (pip alternative) build for the voyager-sdk?This would speed up setup of the sdk and allow easier merging with our development environment.Thanks in advance!

181
Spanner
Axelera Team
K
Cadet
ku15921Cadet
 Metis M.2
Error installing metis-dkms

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 metis-0.07.16 DKMS files...Building for 6.1.99Building for architecture aarch64Building initial module for 6.1.99ERROR (dkms apport): kernel package linux-headers-6.1.99 is not supportedError! Bad return status for module build on kernel: 6.1.99 (aarch64)Consult /var/lib/dkms/metis/0.07.16/build/make.log for more information.dpkg: error pro

26315
Spanner
Axelera Team
V
Cadet
vpc_aiCadet
 Voyager SDK
Trying to build the axstreamer and gstaxstreamer components

Hi Team,I’m working with the Voyager SDK (using docker container) and trying to build the axstreamer and gstaxstreamer components. The source files examples reference:#include <axruntime/axruntime.hpp> (examples/axruntime/axruntime_example.cpp)But I can’t find axruntime.hpp anywhere in the SDK.I’m planning to run inference using a webcam as the input on my mac, with a pipeline that includes ffmpeg and mediamtx for streaming.Is axruntime supposed to be part of the SDK repo, a separate dependency, or is there a script I missed?Thanks!Val.

252
V
Cadet
T
Cadet
triptonCadet
 Metis PCIe
Axelera Metis PCIe AI Accelerator not recognized by lspci

Hey everyone, I’m having trouble getting my Axelera Metis PCIe AI Accelerator to be recognized by `lspci`(and my system in general). I tested the card on two different systems. On my AMD setup, I am using an AMD 5950X with an ASUS B550-F. I tried installing the card in the slot I normally use for my RTX 3080 as well as in another slot that meets the specifications. In both cases, `lspci` does not list the card even though the fan spins and I know it is getting power. Also Voyager SDK dosn’t recognize the card. I also tried it on an Intel system with an Intel i5-8500T on a Supermicro X11SCA-F motherboard. The same issue occurs. The card is powered (fan spin) but not recognized. I noticed that the boot time increases significantly when the accelerator is installed. This makes me think that UEFI might be attempting to detect something, even though no error messages are shown. As I already tried a lot and I couldn’t get it running, I wonder if you have any ideas what I can test.Could there

77132
Spanner
Axelera Team
G
Cadet
GiodstCadet
 Voyager SDK
Error in deploying WASB model

Hi,I get an error when I want to deploy the WASB model for sports ball detection and tracking, converted to onnx with opset 15:ERROR   : Traceback (most recent call last):ERROR   :   File "<frozen compiler.top_level>", line 584, in quantizeERROR   :   File "<frozen qtools_tvm_interface.graph_exporter_v2.graph_exporter>", line 254, in exportERROR   :   File "<frozen qtools_tvm_interface.graph_exporter_v2.graph_exporter>", line 209, in _convert_operatorsERROR   :   File "<frozen qtools_tvm_interface.graph_exporter_v2.replacement_functions>", line 242, in closureERROR   : RuntimeError: Multiple consecutive arithmetic operations by runtime ops found in the graph. This is not allowed presently.ERROR   : ERROR   : The above exception was the direct cause of the following exception:ERROR   : ERROR   : Traceback (most recent call last):ERROR   :   File "/home/aetina/Desktop/voyager-sdk/axelera/app/compile.py", line 456, in compileERROR   :     the_manifest = top_level.c

452
G
Cadet
B
Cadet
brogersaoCadet
 Metis M.2
Newbie question: Does the M.2 card offer plug n play improvements to running a local LLM?

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!

651
Spanner
Axelera Team
llrds
Ensign
llrdsEnsign
 Project Challenge: Recognize & React
Error running standard examples

 Using the Aetina Eval kit that came with the project challenge.Trying to run some of the standard examples, I get this error message:(venv) aetina@aetina:~/voyager-sdk$ ../ll-tests/ll-application.pyWARNING : This model is restricted to deploy for single-core (but can be run using multiple cores).INFO : Deploying model yolov8n-coco-onnx for 1 core. This may take a while...|████████████████████████████████████████| 10:18.7INFO : Deploying model yolov8s-coco-onnx for 1 core. This may take a while...|████████████████████████████████████████| 12:44.9arm_release_ver: g13p0-01eac0, rk_so_ver: 9WARNING : pyglet could not access the display, OpenGL is not available: No standard config is available.[libtriton_linux.c:629] DMA_GET_XFER_SYNC_STATUS failed: Connection timed out[AxeleraDmaBuf.cpp:271] DMABUF_METIS_WAIT failed: Connection timed out[ERROR][waitForAsyncKernelExecOrMemTransfer]: Wait host to dev failed[ERROR][axeCommandQueueExecuteCommandListsAsync]: Waiting for command lists failed: 0

60
llrds
Ensign
saadtiwana
Ensign
saadtiwanaEnsign
 Project Challenge: Recognize & React
How to build Opencv with gstreamer support - compatible with voyager-sdk

Hi,While exploring ways to deploy my application, one possibility I looked at was using gstreamer pipelines to get video into my python-opencv application using appsink. The plan was to then try using the Metis inferencing as a gstreamer pipeline, with the python program interacting with it to feed/get images and results as needed. Anyway, I hit a roadblock with that since I found that the opencv installed with the voyager-sdk installation script is built without gstreamer support. I looked on the internet, and found/modified and tried the following script to build opencv with gstreamer for use with the voyager-sdk: #!/bin/bashOPENCV_VER="4.x"TMPDIR=$(mktemp -d)# Build and install OpenCV from source.cd "${TMPDIR}"git clone --branch ${OPENCV_VER} --depth 1 --recurse-submodules --shallow-submodules https://github.com/opencv/opencv-python.git opencv-python-${OPENCV_VER}cd opencv-python-${OPENCV_VER}export ENABLE_CONTRIB=1export ENABLE_HEADLESS=0# We want GStreamer support enabled.export C

672
saadtiwana
Ensign
G
Cadet
GiodstCadet
 Voyager SDK
Yolo11 with custom weights conversion and deploy

Hi,When trying to deploy yolo11 with custom weights, I noticed a significant performance drop due to the model conversion to onnx. Can I ask what method and parameters were used to convert the axelera yolo11s-coco-onnx model?Thank you!

21220
W
Ensign
S
Cadet
SiegfriedCadet
 Metis M.2
Not enough memory using AxRuntime and M.2 Card on host PC

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, &desc, size, alignment, device, &addr): mem_alloc_device: 249: Exit with error code: 0x70010001 : ZE_RESULT_ERROR_NOT_AVAILAB

495
Spanner
Axelera Team

Badge Winners

Show all badges
Code of Conduct

Address

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

Menu

AI Accelerators

AI Software

Metis Evaluation Systems

Partners

Product Inquiry

Company

Our Story

Our Team

Careers

News

Contact

Reducing CO₂ with
Axelera’s Forest

Follow Us

LinkedIn

Twitter

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  |  Terms of Sale  |  Vulnerability Disclosure Policy

Copyright 2025 © All rights Reserved.