exo-explore
exo is only detecting one of my two 4090
it only sees one GPU.
/ai/exo$ lsb_release -a No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 22.04.5 LTS Release: 22.04 Codename: jammy
/ai/exo$ nvidia-smi
Fri Apr 4 19:32:06 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.230.02 Driver Version: 535.230.02 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 4090 Off | 00000000:01:00.0 Off | Off |
| 0% 39C P0 72W / 480W | 59MiB / 24564MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce RTX 4090 Off | 00000000:03:00.0 Off | Off |
| 0% 32C P8 26W / 480W | 11MiB / 24564MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 3210 G /usr/lib/xorg/Xorg 4MiB | | 0 N/A N/A 6697 C python 20MiB | | 0 N/A N/A 6768 C python 20MiB | | 1 N/A N/A 3210 G /usr/lib/xorg/Xorg 4MiB | +---------------------------------------------------------------------------------------+
/ai/exo$ nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Thu_Nov_18_09:45:30_PST_2021 Cuda compilation tools, release 11.5, V11.5.119 Build cuda_11.5.r11.5/compiler.30672275_0
From what I've witnessed, exo only uses one GPU per device. It may honestly be worth setting up a KVM with GPU passthrough and running another instance of exo to detect the second GPU until a dev picks up the task to support more than one GPU.
