Tuxedo 17 (en Ubuntu 24) + GIGABYTE AORUS RTX 5060 Ti AI Box Carte Graphique - 16GB GDDR7.

Tuxedo17

Je fais l’installation de :

# apt install r8125-dkms
#  modprobe r8152
# lsmod | grep r8152
r8152                 143360  0
mii                    20480  1 r8152

Je vais voir si c’est mieux.

Tuxedo17

Quand je fais “ip a” maintenant je vois la carte réseau :

# ip a
...
4: enxb42e99f45beb: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc fq_codel state DOWN group default qlen 1000
    link/ether b4:2e:99:f4:5b:eb brd ff:ff:ff:ff:ff:ff

Par contre le rename en eth0 semble ne pas fonctionner :


[  269.698536] usb 2-1: New USB device found, idVendor=8087, idProduct=5787, bcdDevice= 0.00
[  269.698539] usb 2-1: New USB device strings: Mfr=1, Product=2, SerialNumber=0
[  269.698540] usb 2-1: Product: USB3 HUB
[  269.698542] usb 2-1: Manufacturer: Intel Corporation
[  269.699313] hub 2-1:1.0: USB hub found
[  269.699348] hub 2-1:1.0: 4 ports detected
[  269.700117] [drm] [nvidia-drm] [GPU ID 0x00000500] Loading driver
[  269.758685] NVRM: objClInitPcieChipset: *** Unable to get PCI port handles
[  269.767623] thunderbolt 0-1: new device found, vendor=0xed device=0x41cd
[  269.767628] thunderbolt 0-1: GIGABYTE AORUS RTX506T AI BOX
[  269.971307] usb 2-1.4: new SuperSpeed Plus Gen 2x1 USB device number 3 using xhci_hcd
[  269.985471] usb 2-1.4: New USB device found, idVendor=0bda, idProduct=0423, bcdDevice= 0.03
[  269.985474] usb 2-1.4: New USB device strings: Mfr=1, Product=2, SerialNumber=0
[  269.985476] usb 2-1.4: Product: 4-Port USB 3.0 Hub
[  269.985476] usb 2-1.4: Manufacturer: Generic
[  269.987177] hub 2-1.4:1.0: USB hub found
[  269.987417] hub 2-1.4:1.0: 4 ports detected
[  270.259256] usb 2-1.4.4: new SuperSpeed USB device number 4 using xhci_hcd
[  270.270966] usb 2-1.4.4: New USB device found, idVendor=0bda, idProduct=8153, bcdDevice=31.00
[  270.270969] usb 2-1.4.4: New USB device strings: Mfr=1, Product=2, SerialNumber=6
[  270.270970] usb 2-1.4.4: Product: USB 10/100/1000 LAN
[  270.270971] usb 2-1.4.4: Manufacturer: Realtek
[  270.270972] usb 2-1.4.4: SerialNumber: 001000001
[  270.334422] r8152-cfgselector 2-1.4.4: reset SuperSpeed USB device number 4 using xhci_hcd
[  270.389518] r8152 2-1.4.4:1.0 eth0: v1.12.13
[  270.401746] r8152 2-1.4.4:1.0 enxb42e99f45beb: renamed from eth0
[  272.362875] NVRM: _issueRpcAndWait: rpcSendMessage failed with status 0x00000011 for fn 76 sequence 583!
[  272.365473] NVRM: kbifInitLtr_GB202: LTR is disabled in the hierarchy
[  274.141227] NVRM: testIfDsmSubFunctionEnabled: GPS ACPI DSM called before _acpiDsmSupportedFuncCacheInit subfunction = 11.
[  274.171854] [drm] Initialized nvidia-drm 0.0.0 for 0000:05:00.0 on minor 0
[  274.172920] nvidia 0000:05:00.0: [drm] Cannot find any crtc or sizes
[  274.172941] pci 0000:05:00.1: extending delay after power-on from D3hot to 20 msec
[  274.173005] pci 0000:05:00.1: D0 power state depends on 0000:05:00.0
[  274.173152] snd_hda_intel 0000:05:00.1: enabling device (0000 -> 0002)
[  274.173265] snd_hda_intel 0000:05:00.1: Disabling MSI
[  274.173276] snd_hda_intel 0000:05:00.1: Handle vga_switcheroo audio client
[  274.173309] snd_hda_intel 0000:05:00.1: number of I/O streams is 30, forcing separate stream tags

Tuxedo17

Plus de crash du wifi…

# boltctl list
 ● GIGABYTE AORUS RTX506T AI BOX
   ├─ type:          peripheral
   ├─ name:          AORUS RTX506T AI BOX
   ├─ vendor:        GIGABYTE
   ├─ uuid:          008b38f1-ba7e-8780-ffff-ffffffffffff
   ├─ generation:    USB4
   ├─ status:        authorized
   │  ├─ domain:     703138df-743c-8780-ffff-ffffffffffff
   │  ├─ rx speed:   40 Gb/s = 2 lanes * 20 Gb/s
   │  ├─ tx speed:   40 Gb/s = 2 lanes * 20 Gb/s
   │  └─ authflags:  none
   ├─ authorized:    jeu. 16 juil. 2026 07:50:20
   ├─ connected:     jeu. 16 juil. 2026 07:50:20
   └─ stored:        ven. 05 juin 2026 15:47:50
      ├─ policy:     iommu
      └─ key:        no

Tuxedo17

Installation :

# apt install displaylink-driver

Car je vois l’erreur :

nvidia 0000:05:00.0: [drm] Cannot find any crtc or sizes

Tuxedo17

Version :

# /usr/local/cuda-13.3/bin/nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2026 NVIDIA Corporation
Built on Tue_Jun_09_02:43:40_PM_PDT_2026
Cuda compilation tools, release 13.3, V13.3.73
Build cuda_13.3.r13.3/compiler.38244171_0

Tuxedo17

J’ai l’impression qu’il y a un bug ouvert : https://github.com/NVIDIA/open-gpu-kernel-modules/issues/979#issuecomment-4172636691 : RTX 5080 via Thunderbolt 5 eGPU: Hard lock on CUDA operations (nvidia-smi works at idle) .

Tuxedo17

Sans l’extenstion :

# llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf 
| model                          |       size |     params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| gemma3 1B Q4_K - Medium        | 762.49 MiB |   999.89 M | CPU        |       8 |           pp512 |        379.86 ± 6.14 |
| gemma3 1B Q4_K - Medium        | 762.49 MiB |   999.89 M | CPU        |       8 |           tg128 |         49.11 ± 0.20 |

build: c3d47e696 (10030)
# nvidia-smi 
Thu Jul 16 11:00:14 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.159.04             Driver Version: 580.159.04     CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| 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 3060 ...    Off |   00000000:01:00.0 Off |                  N/A |
| N/A   43C    P0             24W /  115W |       1MiB /   6144MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

Tuxedo17

Avec l’eGPU :

Il y a une erreur

 1261.324229] NVRM: GPU at PCI:0000:05:00: GPU-5d8d2eb1-648d-e52f-369a-26f078362f02
[ 1261.324235] NVRM: GPU Board Serial Number: 0
[ 1261.324235] NVRM: Xid (PCI:0000:05:00): 79, GPU has fallen off the bus.
[ 1261.324240] NVRM: GPU 0000:05:00.0: GPU has fallen off the bus.
[ 1261.324242] NVRM: GPU 0000:05:00.0: GPU serial number is 0.
[ 1261.324247] NVRM: kgspRcAndNotifyAllChannels_IMPL: RC all channels for critical error 79.
[ 1261.324254] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed!
[ 1261.324263] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed!
[ 1261.324268] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed!
[ 1261.324272] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed!
[ 1261.324388] NVRM: _issueRpcAndWait: rpcSendMessage failed with status 0x0000000f for fn 78 sequence 358!
[ 1261.324391] NVRM: nvCheckOkFailedNoLog: Check failed: GPU lost from the bus [NV_ERR_GPU_IS_LOST] (0x0000000F) returned from nvdEngineDumpCallbackHelper(pGpu, pPrbEnc, pNvDumpState, pEngineCallback) @ nv_debug_dump.c:273
[ 1261.324424] NVRM: _issueRpcAndWait: rpcSendMessage failed with status 0x0000000f for fn 78 sequence 359!

Tuxedo17

Mise à jours avec la dernière version :

# sudo apt-get purge nvidia-* 

# add-apt-repository ppa:graphics-drivers/ppa -y

# apt update 

# apt install nvidia-driver-595 -y

Tuxedo17

Ajout du fichier :

cat  /etc/modprobe.d/nvidia-graphics-drivers.conf 
options nvidia NVreg_EnableGpuFirmware=0

Désactiver le firmware GSP : Si vous utilisez une série RTX 40, parfois le firmware GSP provoque des erreurs NVRM. Empêchez cela en ajoutant NVreg_EnableGpuFirmware=0 à la configuration du pilote

Tuxedo17

Lien à voir : https://github.com/mmhorda/ai-box-rtx-5060ti-egpu-guide

Tuxedo17

Téléchargement des modèles :

# du -sh /models/*
769M    /models/gemma-3-1b-it-q4_k_m.gguf
889M    /models/mmproj-BF16(1).gguf
862M    /models/mmproj-BF16.gguf
885M    /models/mmproj-F16.gguf
5,3G    /models/Qwen3.5-9B-Q4_K_M.gguf
16G     /models/Qwen3.6-27B-Q4_K_M.gguf
21G     /models/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf

Tuxedo17

Check :

# boltctl list
 ● GIGABYTE AORUS RTX506T AI BOX
   ├─ type:          peripheral
   ├─ name:          AORUS RTX506T AI BOX
   ├─ vendor:        GIGABYTE
   ├─ uuid:          008b38f1-ba7e-8780-ffff-ffffffffffff
   ├─ generation:    USB4
   ├─ status:        authorized
   │  ├─ domain:     d02c5899-4b21-8780-ffff-ffffffffffff
   │  ├─ rx speed:   40 Gb/s = 2 lanes * 20 Gb/s
   │  ├─ tx speed:   40 Gb/s = 2 lanes * 20 Gb/s
   │  └─ authflags:  none
   ├─ authorized:    jeu. 16 juil. 2026 11:33:13
   ├─ connected:     jeu. 16 juil. 2026 11:33:13
   └─ stored:        ven. 05 juin 2026 15:47:50
      ├─ policy:     iommu
      └─ key:        no

# boltctl authorize 008b38f1-ba7e-8780-ffff-ffffffffffff

# nvidia-smi 
Thu Jul 16 13:35:11 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.71.05              Driver Version: 595.71.05      CUDA Version: 13.2     |
+-----------------------------------------+------------------------+----------------------+
| 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 3060 ...    Off |   00000000:01:00.0 Off |                  N/A |
| N/A   40C    P0            752W /  115W |       1MiB /   6144MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

J’ai l’erreur :

[   15.841164] NVRM: The NVIDIA GPU 0000:05:00.0 (PCI ID: 10de:2d04)
               NVRM: installed in this system requires use of the NVIDIA open kernel modules.
[   15.841198] NVRM: GPU 0000:05:00.0: RmInitAdapter failed! (0x22:0x56:1017)
[   15.841201] NVRM: GPU 0000:05:00.0: rm_init_adapter failed, device minor number 1

Tuxedo17

Je fais donc :

# apt-get install nvidia-open

Tuxedo17

Nouveau test :

# llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf 
| model                          |       size |     params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| gemma3 1B Q4_K - Medium        | 762.49 MiB |   999.89 M | CPU        |       8 |           pp512 |       371.45 ± 41.49 |
| gemma3 1B Q4_K - Medium        | 762.49 MiB |   999.89 M | CPU        |       8 |           tg128 |         50.31 ± 0.11 |

build: c3d47e696 (10030)
# llama-bench -m /models/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf 
| model                          |       size |     params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| qwen35moe 35B.A3B Q4_K - Medium |  20.60 GiB |    34.66 B | CPU        |       8 |           pp512 |         82.60 ± 2.10 |
| qwen35moe 35B.A3B Q4_K - Medium |  20.60 GiB |    34.66 B | CPU        |       8 |           tg128 |         12.67 ± 0.35 |

build: c3d47e696 (10030)

Tuxedo17

Rien n’est visible :

# nvidia-smi 
Thu Jul 16 14:23:40 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.159.04             Driver Version: 580.159.04     CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| 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 3060 ...    Off |   00000000:01:00.0 Off |                  N/A |
| N/A   45C    P8             11W /  115W |       1MiB /   6144MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
|   1  NVIDIA GeForce RTX 5060 Ti     Off |   00000000:05:00.0 Off |                  N/A |
|  0%   45C    P8              5W /  180W |       2MiB /  16311MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+
# gpustat 
tuxedo-17                              Thu Jul 16 14:23:45 2026  580.159.04
[0] NVIDIA GeForce RTX 3060 Laptop GPU | 45°C,   0 % |     0 /  6144 MB |
[1] NVIDIA GeForce RTX 5060 Ti         | 45°C,   0 % |     1 / 16311 MB |

Tuxedo17

CPU capability :

# nvidia-smi --query-gpu=compute_cap --format=csv
compute_cap
8.6
12.0

Tuxedo17

Nouveau build : ( avec DCMAKE_CUDA_ARCHITECTURES=86 )

#  apt install -y nvidia-cuda-toolkit

#  cd llama.cpp

#  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64

# export PATH=$PATH:$CUDA_HOME/bin

# cmake -B build -DGGML_CUDA=ON  -DCMAKE_CUDA_COMPILER=`which nvcc` -DLLAMA_CURL=ON -DCMAKE_CUDA_ARCHITECTURES=86

# cmake --build build -j$(nproc)

Tuxedo17

Info chouchou : https://github.com/NVIDIA/nvbench/discussions/129

So for your example of a 3090, the compute capability is 8.6. So to build both PTX and SASS for that GPU you would specify -DCMAKE_CUDA_ARCHITECTURES=86.

Tuxedo17

Ajout de nvidia-dkms ( pour noyau personnalisé )

# apt-get install nvidia-dkms-595

A suivre.

NodeBB

Tuxedo 17 (en Ubuntu 24) + GIGABYTE AORUS RTX 5060 Ti AI Box Carte Graphique - 16GB GDDR7.