Server Fault
Sponsored by
Sponsored logo

Questions tagged [gpu]

Ask Question

The tag has no usage guidance.

32 questions
Newest
Active
Bountied
Unanswered
Filter by
Sorted by
Tagged with
0
votes
0answers
7 views

Dual Nvidia RTX A6000 with NVlink?

I wonder how you can link two A6000 cards as shown in this picture from PNY: Dual PNY RTX A6000 connected by NVlink I mean, it looks like one of the cards cannot get air because of the second one. How ...
1
vote
0answers
14 views

What is the best metric for auto-scaling GPU instances for machine learning inference in the cloud?

We have an API in AWS with a GPU instance that does inference. We have an auto-scaler setup with the minimum and maximum number of instances, but aren’t sure which metric (GPU/CPU usage, RAM usage, ...
0
votes
2answers
52 views

Xorg not starting in GKE with GPU : (EE) no screens found(EE)

I am trying to run Xorg server that use GPU inside Google Kubernetes Engine I followed this guide (https://cloud.google.com/kubernetes-engine/docs/how-to/gpus#ubuntu) to setup a GKE cluster with ...
0
votes
0answers
22 views

Using IPMI VGA output for secondary X11 display

I have the Supermicro H12SSL-NT (which is an EPYC server board, but I use it as workstation); it features an on-board VGA chip (ASPEED). I am using a separate graphics card (FirePro V7900) for my ...
0
votes
0answers
46 views

Is there any software VGA dummy solution?

To cut long story short, I actually run Davinci Resolve on a Intel HD 4600 based server on Hetzner auction. And they all don't come with any remote KVM, or use any VGA dummy plug, for every server ...
-1
votes
1answer
139 views

Tesla K80 not showing up in HP DL580 G7

I have a HP Proliant DL580 G7 server with P65 BIOS update from 2015 (which I think is the latest BIOS). I installed the PCIe expansion board in it and installed 4 x Tesla K80 GPUs. Connected them to ...
0
votes
0answers
133 views

Reporting Nvidia GPU usage on Windows Server 2019

We have a few servers with a Nvidia Tesla GPU for machine learning. I want to measure GPU usage on these machines. I already measure CPU and process related details using Powershell. I can also report ...
0
votes
0answers
21 views

Server not starting, after adding graphisc card

First of all, I want to clarify, that I pretty new to server topics. My server runs on normal ubuntu. I bought a Nvidia Quadro k4000. I built it into the server and connected the PCIe Power cable. - ...
0
votes
0answers
34 views

SSH crashes under heavy GPU load but works on CPU

I rely on GPU utilization for work, but the ssh sessions has been crashing under heavy GPU loads for a while now and I can't avoid the issue any longer. What's strange is that the same code works when ...
1
vote
0answers
43 views

Service Creation failed AWS ECS Service with elastic inference accelerator (EIA)

I am trying to create a service in my ECS cluster to run a task that uses elastic inference accelerator (EIA). However, when I try to create the service, I get the following error: I have read the ...
0
votes
1answer
37 views

[GCP]Why can't I see the GPU selection button on my VM instance?

I want to use GPU in Windows VM. However, the GPU selection button is not active when creating the instance. Currently, I applied for GPU(k-80) as a quota and got 1 allocation. Of course, I received ...
1
vote
1answer
368 views

Considerations using consumer class (high-end) GPU in server?

Motivation: First of all, even if I have some knowledge of computer science, software development and server Linux administration, I never looked into a server hardware and I am a total "newbie&...
0
votes
1answer
22 views

Configure a new kubernetes node automatically

I configured a Kubernetes cluster with GPU in AWS, and one of the steps is configuring the nodes to enable Nvidia runtime by default. So when I configured cluster auto scaler, the cluster scales up ...
0
votes
0answers
97 views

Deep Learning - maximum GPUs a CPU can handle

The design for the deep learning server would be very similar to that of a mining rig, specifically using risers to stack as many GPU's onto the motherboard. The design is as follows: CPU: AMD EPYC ...
0
votes
0answers
26 views

Mounting virtual GPUs on different machines

I have multiple computers connected over a VPN, each computer having one or more Nvidia GPUs. All computers run Linux. I'm wondering if it's possible to mount them over network such that they appear ...
0
votes
1answer
118 views

How to increase Service name: GPU (ALL REGION) quota limit in Compute Engine?

I requested 2 times for GPU all region service quota from 0 to 1 but not got accepted so ,I want a way to increase this limit.
0
votes
0answers
106 views

Make Headless Server Use Hardware Accelaration

I have a headless CentOS 8 Server with an AMD GPU. I want to use hardware acceleration but when I run OpenGL programs with xvfb-run (e.g glxinfo), the system reports I am using software rendering. How ...
0
votes
0answers
49 views

SGE for single CUDA GPU with multiple jobs

I have been using the SGE (8.1.9) system for a while that runs fine for scheduling CPU jobs. I have a machine with 14 CPUs and 1 GPU running Ubuntu server 18.04. I would like to incorporate the GPU ...
0
votes
1answer
40 views

Create a kubernetes master on google cloud and add as nodes on-premise instances with gpu

Since we are working on ML engineering tasks we do have requirements of gpu instances. We do have couple of them on-premise and we need to organize our pipeline creating a kubernetes cluster. Since ...
1
vote
1answer
496 views

Misbehaving NVLINK with 2080 ti cards?

I am running into problems with nvlink'd RTX videocards, and I wonder if someone more experienced with this tech could kindly look at the output below and tell me if there is a problem? Using a pair ...
0
votes
0answers
246 views

RTX 2070 + Fedora 31: nvidia_modeset error freezes computer just before login

I'm experimenting an error -which I'll describe next- with the following Linux system: Fedora 31 - kernel: 5.5.17-200.fc31.x86_64 GPU is ASUS RTX 2070 SUPER with drivers 440.82, also CUDA 10.1 and ...
2
votes
1answer
4k views

Use passthrough GPU in KVM/QEMMU and display in host OS in a window

I'm new to KVM/QEMMU. I have used virtual box to run Windows 10 in a virtual machine on my Arch host system (a laptop with both integrated and discrete GPUs). Being dissatisfied with the video ...
2
votes
3answers
2k views

Why are GPUs accessible from docker containers running on Linux hosts, but not on Windows or MacOS hosts?

Recent versions of docker (or any version of nvidia-docker) allow direct(?) access to the host GPU from within docker containers, with full access to CUDA APIs. This is very convenient when deploying ...
0
votes
0answers
54 views

GPU Passthrough on Xen Hypervisor

I have a Dell PowerEdge r710 running the Xen hypervisor and I want to get a decent graphics card for a virtual machine. I plan on doing GPU passthrough to dedicate the entire GPU to the virtual ...
0
votes
1answer
1k views

Compatible AMD GPU for the Dell PowerEdge r710 [closed]

I'm a complete noob when it comes to server virtualization and GPUs, so please bear with me. Are there any decent AMD GPUs that are easily compatible with the Dell PowerEdge r710? I'm looking for ...
0
votes
1answer
32 views

Resolved - Only 1 nodes out of 2 have registered on my node-pool if I have a GPU activated on my cluster

I have a managed k8S cluster with 1GPU (Tesla K80) activated in west1-b and west1-d (Each zone has this GPU model enabled, and my quota is ok). Each time that I create a node pool with 2 nodes only ...
1
vote
1answer
41 views

always available gpu servers

I need several GPU servers for rendering. Region doesn`t matter. Preemptible - I think it is ok for me. It is important that at any time I should be able to run a couple of instances with the GPU. ...
0
votes
1answer
49 views

I can't use a graphics card on my vm [duplicate]

I can't use a gpu on my vm and it says: Quota 'GPUS_ALL_REGIONS' exceeded. Limit: 0.0 globally all the time and I have premium so how do I fix this?
1
vote
0answers
40 views

How Do You Run GPU Task on Windows Server 2016 Remotely?

From my understanding, remotely executing GPU tasks is a little tricky because of the way sessions work on Windows. Session 0 does not have access to GPU drivers, and usually when you remotely execute ...
1
vote
0answers
91 views

DDA device out of resource(Error 12) in Hyper-V VM

We're 'borrowing' a server from an IDC that had two Tesla V100 on it. It runs Windows Server 2016. Since it has some impressive graphics capabilities, we were looking for ways to run graphic ...
2
votes
0answers
2k views

Quota 'GPUS_ALL_REGIONS' exceeded. Limit: 0.0 globally [duplicate]

I am trying to create the VM instance with NVIDIA K80 GPUs in Asia-East1 so, I requested to increase the quota and team have adjusted the quota. However, when I am trying to create the VM instance by ...
0
votes
1answer
2k views

Unable to use gpu in azure windows server 2016

I am trying to run a GPU intensive application(Lumion) on the Azure cloud. Image used - Windows Server 2016. Hardware - NV6_Promo with 1xK80 GPU. Any application, when launched, run without using ...

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.