1 hour ago, Renew said:

Any thoughts? ideas? is this a 7.3 issue? or?

Just to male sure, Ollama didnmt receive an update correct? Just to rule put that possibility since Ollama receives updates often.

Do you also have the docker run conmand from your Ollama container?

I'll look into your Diagnostics later.

EDIT: I don't see anything obvious from your Diagnostics @Renew. Can you issue nvidia-smi in the container and see if both GPUs are showing up.

You can also try to create an environment variable with the Key: CUDA_VISIBLE_DEVICES and as Value set: 0,1 in your Ollama Docker template.

cant downgrade to 580 driver: Can't download Nvidia Driver Package v580.159.03. How to do it manually ?

UPDATE: NVMND i reinstalled the plugin and it works

Edited May 19May 19 by Gee1

On 5/16/2026 at 12:30 AM, ich777 said:

As pointed oit in the previous threads use --gpus=all

--gpus=all causes the container to fail to start.

The container only starts if Extra Parameters is left blank, with Nvidia_visible_devices set to my GPU UUID and Nvidia_driver_capabilities set to all (which worked fine with --runtime=nvidia before going to 7.3 from 7.2.4).

So without an extra parameter (hw) transcoding does not happen, only slams my processor h.264.

2 hours ago, marlinz357 said:

--gpus=all causes the container to fail to start.

Diagnostics please when the driver is installed and after trying to run a container.

On 5/17/2026 at 12:27 PM, viniciustp said:

Here it is. Thank you in advance for the help!

From the diagnostics that you've posted I see anything obvious.

To fully reinstall the driver:
1. Remove the plugin

2. Reboot

3. Install the plugin again

4. Select your preferred driver

5. Reboot

On 5/19/2026 at 12:01 AM, ich777 said:

Diagnostics please when the driver is installed and after trying to run a container.

Thank you for your help

diagnostics-20260519-2054.zip

Hi all,

I’m having trouble getting my NVIDIA GeForce RTX 5060 Ti (GB206, Blackwell) working with the Nvidia Driver plugin on Unraid.

System:

• Unraid OS: 7.2.4

• GPU: NVIDIA GeForce RTX 5060 Ti (lspci shows GB206)

• Motherboard: ASUS X99‑A/USB 3.1 (LGA2011‑v3)

• Current Nvidia Driver (per plugin): 595.71.05 (open‑source)

Symptoms:

• The Nvidia Driver plugin page shows:

  • Nvidia Driver Version: 595.71.05

  • Open Source Kernel Module: Yes

  • Installed GPU(s): “No devices were found”

• lspci clearly sees the card:

01:00.0 VGA compatible controller: NVIDIA Corporation GB206 [GeForce RTX 5060 Ti] (rev a1)

01:00.1 Audio device: NVIDIA Corporation GB206 High Definition Audio Controller (rev a1)

lsmod shows NVIDIA modules loaded (no nouveau):

nvidia_uvm

nvidia_drm

nvidia_modeset

nvidia

nvidia-smi on the host returns:

No devices were found

Key NVRM errors from dmesg/syslog:

I’m seeing repeated initialization failures like:

NVRM: GPU0 kbusVerifyBar2_GB202: MMUTest BAR2 readback VA = 0x0 returned garbage ...

NVRM: GPU0 nvAssertOkFailedNoLog: Assertion failed: Generic memory error [NV_ERR_MEMORY_ERROR]

NVRM: GPU0 RmInitNvDevice: *** Cannot initialize the device

NVRM: GPU 0000:01:00.0: RmInitAdapter failed! (0x24:0x72:1344)

NVRM: GPU 0000:01:00.0: rm_init_adapter failed, device minor number 0

...

NVRM: GPU0 _kgspBootGspRm: unexpected WPR2 already up, cannot proceed with booting GSP

NVRM: GPU0 RmInitAdapter: Cannot initialize GSP firmware RM

NVRM: GPU 0000:01:00.0: RmInitAdapter failed! (0x62:0x40:2168)

NVRM: GPU 0000:01:00.0: rm_init_adapter failed, device minor number 0

These repeat many times during boot and whenever the driver appears to attempt initialization.

What I’ve already tried:

• Used the Nvidia Driver plugin to switch driver versions within the 595.x family (open‑source and production where available).

• Uninstalled the Nvidia Driver plugin, rebooted, reinstalled it from Apps, selected the recommended driver, clicked Update & Download, and rebooted again.

• Verified the card is visible via lspci, that nvidia modules are loaded, and that nouveau is not present.

• Confirmed no VMs are configured to pass through this GPU.

The behavior is always the same: modules load, lspci sees the GPU, but RmInitAdapter fails and nvidia-smi reports no devices.

Why I think this might be a driver/Blackwell issue:

Searching around, I found similar reports on Linux for new RTX 50‑series / Blackwell cards with errors like _kgspBootGspRm: unexpected WPR2 already up, cannot proceed with booting GSP and RmInitAdapter failed (e.g., RTX 5090/5080 threads on NVIDIA’s forums and an issue titled “RmInitAdapter failed on Fedora 43 for RTX 5060 Ti”). These look very similar to what I’m seeing on Unraid

23 hours ago, marlinz357 said:

Thank you for your help 168.24 kB · 1 download

diagnostics-20260519-2054.zip

ich777, please let me know when you get a chance to view my diagnostics above.

19 hours ago, marlinz357 said:

ich777, please let me know when you get a chance to view my diagnostics above.

Please read the first post (big red text):

May 18 21:24:42 Gandalf emhttpd: /usr/local/emhttp/plugins/user.scripts/backgroundScript.sh "/tmp/user.scripts/tmpScripts/unlock nvidia/script" >/dev/null 2>&1

On 5/21/2026 at 7:47 AM, wtam63 said:

I’m having trouble getting my NVIDIA GeForce RTX 5060 Ti (GB206, Blackwell) working with the Nvidia Driver plugin on Unraid.

Do you have Diagnostics?

22 hours ago, ich777 said:

Please read the first post (big red text):

May 18 21:24:42 Gandalf emhttpd: /usr/local/emhttp/plugins/user.scripts/backgroundScript.sh "/tmp/user.scripts/tmpScripts/unlock nvidia/script" >/dev/null 2>&1

ich777, I don't see any big red text above.... not sure what you mean?

20 minutes ago, marlinz357 said:

ich777, I don't see any big red text above.... not sure what you mean?

I'm also not sure where you where looking:

I updated the nvidia-driver plugin, and the new driver v580.159.03 is not working fine in my M2000, I checked the last verison what I use without problems in my backup and I used nvidia-580.126.18-6.12.54-Unraid-1.

How I can continue using the old version version?

Thanks so much.

On 5/23/2026 at 4:24 PM, ich777 said:

I'm also not sure where you where looking:

Thank you, however this is exactly what I have had for over two years now and it has worked great, but since the moment I updated unraid from 7.2.4 directly to 7.3.0 it stopped working..

10 hours ago, milfer322 said:

Thanks so much.

Diagnostics please.

5 hours ago, marlinz357 said:

Thank you, however this is exactly what I have had for over two years now and it has worked great, but since the moment I updated unraid from 7.2.4 directly to 7.3.0 it stopped working..

Don't know what you are saying, please remove your unlock scirpt, until then no further support.

On 5/26/2026 at 2:47 AM, ich777 said:

Don't know what you are saying, please remove your unlock scirpt, until then no further support.

What I was saying is that I have followed all the instructions in your original post for two years without any issue until updating to 7.3, then the issue immediately started (which means I am now not able to have anything in extra parameters box or the plex app won't start). Additionally, I had to figure out what an unlock script even is and have deleted it. Not sure why that matters but I am not that tech savvy with computers, and had a friend help me. So what can I do now to have my GPU transcode once again since I lost that ability with the Unraid 7.3 update?

getting following after updating to 7.3.1 today, okex will no longer load

any ideas?>

thanks

Myk

+==============================================================================
| WARNING - WARNING - WARNING - WARNING - WARNING - WARNING - WARNING - WARNING
|
| Don't close this window with the red 'X' in the top right corner until the 'DONE' button is displayed!
|
| WARNING - WARNING - WARNING - WARNING - WARNING - WARNING - WARNING - WARNING
+==============================================================================

----------------Downloading Nvidia Driver Package v580.159.04-----------------
---------This could take some time, please don't close this window!------------

---------------Can't download Nvidia Driver Package v580.159.04----------------

Nvidia Info:

Nvidia Driver Version: 610.43.02

Open Source Kernel Module: No

Installed GPU(s):
NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running.

GPU Driver Support:

84:00.0: VGA compatible controller [0300]: NVIDIA Corporation GP107GL [Quadro P400]
Detected via: lspci
Chip codename: GP107GL
Architecture: Pascal
Kernel module support: proprietary-only
Device ID input: 10de:1cb3
Normalized ID: 1cb3
Supported candidates: 580.159.04
Recommended Driver: 580.159.04 (best-available)

GPU-based driver filtering is enabled.

Deprecated: trim(): Passing null to parameter #1 ($string) of type string is deprecated in/usr/local/emhttp/plugins/dynamix/include/DefaultPageLayout/evalContent.php(34) : eval()'d codeon line326

Deprecated: trim(): Passing null to parameter #1 ($string) of type string is deprecated in/usr/local/emhttp/plugins/dynamix/include/DefaultPageLayout/evalContent.php(34) : eval()'d codeon line326

Edited May 29May 29 by MyKroFt

2 hours ago, MyKroFt said:

getting following after updating to 7.3.1 today, okex will no longer load

Please see this recommended post, your plugin is broken when you see the Deprecated lines:

Just a reminder for next time, always include Diagnostics.

On 5/29/2026 at 12:03 AM, ich777 said:

Please see this recommended post, your plugin is broken when you see the Deprecated lines:

Just a reminder for next time, always include Diagnostics.

thank you much, all fixed

Myk

ich777, are you going to help me?

Just now, marlinz357 said:

ich777, are you going to help me?

I don't know what to say.

You have to ask your friend who set this all up, issue with that is that he set something up to circumvent certain restrictions and I can't tell if that's what's all causing that or anything else.

You first have to get rid of that script which I don't know where it lives maybe he set it up as a user script maybe he did something else.

Even if you remove the driver the script will stay because he put it in place and this is nothing the plugin can fix.

5 minutes ago, ich777 said:

I don't know what to say.

You have to ask your friend who set this all up, issue with that is that he set something up to circumvent certain restrictions and I can't tell if that's what's all causing that or anything else.

You first have to get rid of that script which I don't know where it lives maybe he set it up as a user script maybe he did something else.

Even if you remove the driver the script will stay because he put it in place and this is nothing the plugin can fix.

the script was in the "user scripts" plugin, and we found it and deleted it. There just seems to be something with the updated docker that occured with the move to 7.3. Is there any other diagnostics that could help you figure out why I can't transcode with gpu suddenly?

The following is the last line of the "command failed" when trying to input --runtime=nvidia in extra parameters:

docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error jailing process inside rootfs: open /proc/self/mountinfo: no such file or directory

Does this explain anything meaningful to you?

20 minutes ago, marlinz357 said:

The following is the last line of the "command failed" when trying to input --runtime=nvidia in extra parameters:

docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error jailing process inside rootfs: open /proc/self/mountinfo: no such file or directory

Does this explain anything meaningful to you?

Please try to use --gpus all