RKNN ML smart search error
Hi everyone，I'm currently using Rk3588 board and encountered some problem on clip features.
After all ml settings are finished. the utilization of NPU is above 0 while doing facing recognition and smart searching processes .
but when I try to use text searching feature , it will showing up immich server error.
here is the immch-machine-learning log
I know that this is because RKNN library miss some operation , but any suggestions on alternative way rather than using cpu?
I RKNN: [03:21:34.838] RKNN Driver Information, version: 0.9.8
I RKNN: [03:21:34.841] RKNN Model Information, version: 6, toolkit version: 2.3.0(compiler version: 2.3.0 (c949ad889d@2024-11-07T11:39:30)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
E RKNN: [03:21:35.835] Unsupport CPU op: CumSum in this librknnrt.so
W RKNN: [03:21:35.836] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
[03/31/25 03:21:39] I Loaded RKNN model from
/cache/clip/XLM-Roberta-Large-ViT-H-14__frozen_laio
n5b_s13b_b90k/textual/rknpu/rk3588/model.rknn with
3 threads.
[03/31/25 03:22:07] ERROR Worker (pid:10) was sent code 139!
5 Replies
:wave: Hey @atsrx,
Thanks for reaching out to us. Please carefully read this message and follow the recommended actions. This will help us be more effective in our support effort and leave more time for building Immich :immich:.
References
- Container Logs:
docker compose logs docs
- Container Status: docker ps -a docs
- Reverse Proxy: https://immich.app/docs/administration/reverse-proxy
- Code Formatting https://support.discord.com/hc/en-us/articles/210298617-Markdown-Text-101-Chat-Formatting-Bold-Italic-Underline#h_01GY0DAKGXDEHE263BCAYEGFJA
Checklist
I have...
1. :blue_square: verified I'm on the latest release(note that mobile app releases may take some time).
2. :blue_square: read applicable release notes.
3. :blue_square: reviewed the FAQs for known issues.
4. :blue_square: reviewed Github for known issues.
5. :blue_square: tried accessing Immich via local ip (without a custom reverse proxy).
6. :blue_square: uploaded the relevant information (see below).
7. :blue_square: tried an incognito window, disabled extensions, cleared mobile app cache, logged out and back in, different browsers, etc. as applicable
(an item can be marked as "complete" by reacting with the appropriate number)
Information
In order to be able to effectively help you, we need you to provide clear information to show what the problem is. The exact details needed vary per case, but here is a list of things to consider:
- Your docker-compose.yml and .env files.
- Logs from all the containers and their status (see above).
- All the troubleshooting steps you've tried so far.
- Any recent changes you've made to Immich or your system.
- Details about your system (both software/OS and hardware).
- Details about your storage (filesystems, type of disks, output of commands like fdisk -l and df -h).
- The version of the Immich server, mobile app, and other relevant pieces.
- Any other information that you think might be relevant.
Please paste files and logs with proper code formatting, and especially avoid blurry screenshots.
Without the right information we can't work out what the problem is. Help us help you ;)
If this ticket can be closed you can use the /close command, and re-open it later if needed.I believe there's an open issue for this on github
okay I did not find any useful at that moment. after many test right now I just give up to use multilanguage model. seems all english model works fine but all Chinese not.
I also haven't able to find a way to implement CumSum in RKNPU yet
The way the docs mentioned doesn't work on those large models
:1193388615347216464: