After running “hailomz compile” with my trained model .onnx on raspberrypi5 with hat
got such error
[HailoRT] [error] HEF format is not compatible with device. Device arch: HAILO8L, HEF arch: HAILO8
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INVALID_HEF(26)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INVALID_HEF(26)
Traceback (most recent call last):
File “/usr/local/lib/python3.10/site-packages/hailo_platform/pyhailort/pyhailort.py”, line 2643, in configure
configured_ngs_handles = self._vdevice.configure(hef._hef, configure_params_by_name)
hailo_platform.pyhailort._pyhailort.HailoRTStatusException: 26
How can i compile a file needed for my device?
Thank you
1 Like
Already found decision
we should run compile with “–hw-arch hailo8l” line
6 Likes
Welcome to the Hailo Community!
Well done.
jiapei
November 5, 2024, 7:05am
4
Let me continue this topie.
How to convert the HEF provided by tappas
tappas/apps/h8/gstreamer/resources/hef
➜ hef git:(master) ✗ ls
arcface_mobilefacenet_nv12.hef lprnet.hef scrfd_10g_nv12.hef yolov5m_vehicles.hef
arcface_mobilefacenet_v1.hef mspn_regnetx_800mf.hef scrfd_2.5g.hef yolov5m_wo_spp_60p.hef
centerpose_regnetx_1.6gf_fpn.hef nanodet_repvgg.hef ssd_mobilenet_v1.hef yolov5n_seg.hef
fast_depth.hef repvgg_a0_person_reid_2048.hef ssd_mobilenet_v1_visdrone.hef yolov5s_personface_reid.hef
joined_centerpose_repvgg_a0_center_nms_joint_nms.hef resnet_v1_50.hef tddfa_mobilenet_v1.hef yolov8m.hef
lightface_slim.hef scrfd_10g.hef tiny_yolov4_license_plates.hef yolovx_l_leaky.hef
to be HAILO8L compatible??? for I got the same error messages:
[HailoRT] [error] HEF format is not compatible with device. Device arch: HAILO8L, HEF arch: HAILO8
Could you please provide more details?
I’m trying to execute models from model_zoo repository but they all raise the same error you reported: [HailoRT] [error] HEF format is not compatible with device. Device arch: HAILO8L, HEF arch: HAILO8
KlausK
April 10, 2025, 5:51pm
6
The Model Zoo also contains models compiled to the Hailo-8L.
GitHub - Hailo Model Zoo - Public Models - HAILO8L
Note: You can run models compiled for Hailo-8L on a Hailo-8 device but not the other way around. You will get a warning from HailoRT because the model will only use the resources that are available on a Hailo-8L device and therefore in many cases the performance will be lower.
jiapei
September 6, 2025, 1:34pm
7
In my Docker, I still keep failing to building the .hef out with these 2 errors:
[error] Failed to produce compiled graph
[error] TypeError: expected str, bytes or os.PathLike object, not NoneType
And on my raspberry Pi 5, if I use models metioned on hailo_model_zoo/docs/public_models/HAILO8L at master · hailo-ai/hailo_model_zoo · GitHub , I’m getting another error:
➜ Downloads hailortcli run resnet_v1_18.hef
Running streaming inference (resnet_v1_18.hef):
Transform data: true
Type: auto
Quantized: true
[HailoRT] [error] CHECK failed - max_desc_page_size given 16384 is bigger than hw max desc page size 4096
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8)
[HailoRT CLI] [error] CHECK_SUCCESS failed with status=HAILO_INTERNAL_FAILURE(8) - Failed configure vdevice from hef
➜ Downloads
Can anybody please do help???
omria
September 8, 2025, 12:14pm
8
Hey @jiapei ,
For the rpi thing, check out this fix: hailo-rpi5-examples/doc/install-raspberry-pi5.md at main · hailo-ai/hailo-rpi5-examples · GitHub
About that docker error you’re getting - the “Failed to produce compiled graph” with the Python NoneType issue is usually because something’s missing. Could be a few things:
You might need to specify the Hailo-8L chip
Check if your model file paths are correct
Make sure Docker can actually see your files (volume mounting issues are common)
Give those a shot and see what happens. If you’re still stuck, just post a new topic with your docker run command or compose file and I’ll take a look.