Greetings, this is my first time posting a topic on the forums, so I hope this issue hasn’t already been covered on here (I couldn’t find any posts about this specific issue). After upgrading to the 575xx series of drivers, after some time the system loses access to the dedicated GPU completely, wi…

Hi @gimzie , Could you try after applying @aplattner 's patch : suspend/resume fixes · NVIDIA/open-gpu-kernel-modules@c7e7213 · GitHub . This fix will be present in the next driver release.

Applied the patch and attempted to suspend/unsuspend; it seems like it works! The dmesg log still reports an “out of memory” error, but the suspend does not seem to fail and the GPU is still accessible as normal. I also confirmed that the open kernel modules are in use, so it appears that the patch …

Update: Unfortunately, while general GPU use seems fine with this patch and software is able to render using the GPU, i.e. vkcube or glxgears, CUDA functionality seems to intermittently disappear. As a result, NVENC encoding is made unavailable in applications such as ffmpeg. I was able to get NVEN…

Not sure, as every time it would report “out of memory” problems, the system had plenty of both VRAM and RAM available, which in theory means shared VRAM wouldn’t be necessary to unsuspend?

Same. My PC freezes a few minutes after this appears in the logs. Even hard freezes that forces me to power off manually. nvidia-bug-report.log.gz (1.3 MB)

I’m encountering the same problem daily. After a while CUDA just stops working completely, and I can see the following error in dmesg: [32563.824015] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1…

For anyone still experiencing this problem on Linux, it seems that RAM fragmentation is the issue. You can solve this by syncing and dropping the memory cache. My script looks like this: #!/bin/bash ERR_TEXT=“NV_ERR” LOOKBACK_MIN=5 ERR_LINE=$(sudo dmesg | grep $ERR_TEXT | tail -n 1) echo $ERR_…

i had a similar issue on 550.x where using cuda after STR didn’t work anymore. For me the workaround was to unload nvidia-uvm kernel module and load it again e.g.: rmmod nvidia-uvm modprobe nvidia-uvm

[575.64] NVRM Out of memory error causes dGPU to not be usable after some time

Graphics / Linux Linux

renari July 6, 2025, 5:58am 6

Possibly related to this? Non-existent shared VRAM on NVIDIA Linux drivers

Topic		Replies	Views
Sometimes unable to suspend OS: Failed to map NvKmsKapiMemory Linux	14	1132	September 3, 2026
Nvidia driver (570.144) crash on suspend and freeze whole system Linux kernel , wayland , linux-driver , sleep_mode	9	1093	November 14, 2025
NVIDIA 610.43.03 driver: NV_ERR_NO_MEMORY causes full system freeze on hybrid laptop (RTX 5060) Linux laptop , linux-driver	0	142	July 31, 2026
Constant X crashes when resuming from suspend to ram with external VGA display connected Linux	5	2103	February 27, 2017
Failed to allocate vmap() page descriptor table when suspending to S3 Linux	4	691	November 26, 2024
BUG: nvidia_uvm needs to be removed and re-inserted in order to work after wakeup from suspend Linux driver	23	8188	May 23, 2025
Nvidia driver crashes randomly when gpu is used on 565 Linux	1	947	November 22, 2024
NVIDIA unusable in Ubuntu 20.10 (volatile GPU RAM crap) Linux	4	881	January 11, 2021
GPU has fallen off the bus Linux linux , gpu , linux-driver	6	645	August 14, 2025
Driver 390.59-8.1; kernel-default-4.16.11-1.6; xen-4.10.1_02-1.1: out of memory: openSUSE Tumbleweed Linux	1	960	May 31, 2018

[575.64] NVRM Out of memory error causes dGPU to not be usable after some time

Related topics