NodeBB

Je vais essayer la version Docker : # export MODEL_PATH='/models/' # docker run --privileged --network=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ipc=host --shm-size 16G -v $MODEL_PATH:/data rocm/llama.cpp:llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full -m /data/Qwen3.6-27B-Q4_K_M.gguf -p "Building a website can be done in 10 simple steps:" -n 512 --n-gpu-layers 999 Unable to find image 'rocm/llama.cpp:llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full' locally llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full: Pulling from rocm/llama.cpp 757fe5b21110: Downloading [==> ] 6.291MB/114.7MB 0f1832fb3fb1: Downloading [> ] 5.243MB/646.4MB 52ae0682347f: Downloading [======================================> ] 107MB/138.7MB b00fa23324d1: Pull complete

Requete pour la compression : { "messages": [ { "role": "user", "content": "You are a summarization agent creating a context checkpoint. Treat the conversation turns below as source material for a compact record of prior work. Produce only the structured summary; do not add a greeting, preamble, or prefix. Write the summary in the same language the user was using in the conversation — do not translate or switch to English. NEVER include API keys, tokens, passwords, secrets, credentials, or connection strings in the summary — replace any that appear with [REDACTED]. Note that the user had credentials present, but do not preserve their values.\n\nCreate a structured checkpoint summary for the conversation after earlier turns are compacted. The summary should preserve enough detail for continuity without re-reading the original turns

Temps : [image: 1786011735209-llama-swap-daily-duration-resized.png]

Report fait : https://www.ovhcloud.com/en/abuse/?validation_uuid=ce4dbaeb-ef3a-4966-b35b-5f5800dc9720

Update : [image: 1785824547990-a7b01039-de7f-4239-a35e-d05da2d0e7c8-image.png]

Toujours la même erreur : # ./nodebb upgrade Updating NodeBB... 1. Updating package.json file with defaults... OK 2. Bringing base dependencies up to date... started npm notice run nodebb@4.14.6 postinstall npm notice run if [ "$NODE_ENV" != "production" ]; then npx husky install; fi changed 4 packages, and audited 833 packages in 10s 129 packages are looking for funding run `npm fund` for details 8 vulnerabilities (1 moderate, 7 high) To address issues that do not require attention, run: npm audit fix To address all issues (including breaking changes), run: npm audit fix --force Run `npm audit` for details. 3. Checking installed plugins for updates...Checking installed plugins and themes for updates... OK A total of 2 package(s) can be upgraded: * @nodebb/nodebb-plugin-reactions (3.0.3 -> 3.0.4) * nodebb-plugin-feed (4.0.1 -> 4.0.3) Proceed with upgrade (y|n)? y Upgrading packages... 4. Updating NodeBB data store schema... Parsing upgrade scripts... OK | 0 script(s) found, 182 skipped Schema update complete! 5. Rebuilding assets... started 2026-08-04T06:20:09.785Z [4567/57604] - info: [build] Building in parallel mode 2026-08-04T06:20:09.787Z [4567/57604] - info: [build] plugin static dirs build started 2026-08-04T06:20:09.787Z [4567/57604] - info: [build] requirejs modules build started 2026-08-04T06:20:09.788Z [4567/57604] - info: [build] client js bundle build started 2026-08-04T06:20:09.788Z [4567/57604] - info: [build] admin js bundle build started 2026-08-04T06:20:09.789Z [4567/57604] - info: [build] client side styles build started 2026-08-04T06:20:09.789Z [4567/57604] - info: [build] admin control panel styles build started 2026-08-04T06:20:09.791Z [4567/57604] - info: [build] templates build started 2026-08-04T06:20:09.791Z [4567/57604] - info: [build] languages build started 2026-08-04T06:20:10.316Z [4567/57604] - info: [build] plugin static dirs build completed in 0.528sec 2026-08-04T06:20:11.821Z [4567/57604] - info: [build] client js bundle build completed in 2.033sec 2026-08-04T06:20:11.821Z [4567/57604] - info: [build] admin js bundle build completed in 2.033sec 2026-08-04T06:20:15.137Z [4567/57604] - info: [build] requirejs modules build completed in 5.35sec 2026-08-04T06:20:15.138Z [4567/57604] - info: [build] Bundling with Webpack. [10%] building (0/0 modules) 2026-08-04T06:20:16.987Z [4567/57604] - info: [build] client side styles build completed in 7.197sec [10%] building (23/245 modules) [10%] building (411/496 modules) 338 assets 541 modules ERROR in ./build/public/scripts-client.js 3435:5 Module parse failed: Unexpected token (3435:5) You may need an appropriate loader to handle this file type, currently no loaders are configured to process this file. See https://webpack.js.org/concepts#loaders | }); | > ;CC0 1.0 Universal | | Statement of Purpose webpack 5.108.4 compiled with 1 error in 10848 ms 2026-08-04T06:20:27.656Z [4567/57604] - info: [build] Asset compilation successful. Completed in 17.861sec. NodeBB Upgrade Complete!

# grep "wp-login.php" /var/log/apache2/access.*.log.1 | sed 's/:/ /g' | awk '{print $2}' | sort -n | uniq -c | sort -n | tail -10 4 91.246.51.140 6 165.231.121.77 6 191.102.165.71 22 2.57.23.72 24 38.253.224.3 58 178.128.84.251 1454 139.162.58.217 1472 165.22.58.190 1868 139.162.58.164 4216 172.104.172.245

[image: 1785390482492-7c9f6dc6-b13d-45ef-98c1-88771c3e3e93-image.png] [image: 1785390541176-654ab7f4-a802-490e-bf51-476c7c37fa80-image.png]

J’avais oublier de modifier le script /usr/local/bin/aorus-bridge . VENDOR_ID="${VENDOR_ID:-0x10de}" # NVIDIA # DEVICE_ID: exact PCI device id to match (e.g. 0x2b85 for RTX 5090). Leave # empty to match ANY NVIDIA display controller by PCI class — this covers the # whole RTX 50-series (5090=0x2b85, 5060 Ti=0x2d04, …) without a hardcoded list, # in the same spirit as is_tb_tunneled below. Set DEVICE_ID to pin one board. DEVICE_ID="${DEVICE_ID:-0x2d04}" # PCI base class 0x03 = display controller (VGA 0x0300 / 3D 0x0302); selects the # GPU function and excludes its HDMI-audio function (class 0x0403). GPU_CLASS_PREFIX="${GPU_CLASS_PREFIX:-0x03}"

J’ai fait un post : https://community.nodebb.org/ [image: 1785136048007-59b5581b-041a-4f1b-b7e2-2ebefa6f4ff2-image.png]

Encore une augmentation de la charge … [image: 1784906731024-ec1c3ea3-c454-4949-99b2-c7835da5995e-image.png] [image: 1784906751639-6b0fd06d-34d0-4606-bb11-49a2512f4378-image.png]

j’ai pas fait de reboot depuis 150 jours … # uptime 17:18:26 up 150 days, 22:30, 0 users, load average: 7.41, 7.81, 7.79 # uname -a Linux balkany 6.17.9-1-pve #1 SMP PREEMPT_DYNAMIC PMX 6.17.9-1 (2026-01-12T16:25Z) x86_64 GNU/Linux

Sur l’interface : [image: 1784730275084-20dcbc69-b2f8-4227-a6ca-368c352f2d2a-image.png]

A tester https://github.com/HalfbitStudio/hermes-plugin-rocketchat .

Nouveau test : # llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf -dev CUDA0 -fa on --threads 12 -ngl 999 --cache-type-v q8_0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | threads | type_v | fa | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | -----: | --: | ------------ | --------------: | -------------------: | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | CUDA0 | pp512 | 387.17 ± 2.25 | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | CUDA0 | tg128 | 18.31 ± 0.01 | # llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf -fa on --threads 12 -ngl 999 --cache-type-v q8_0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | threads | type_v | fa | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | -----: | --: | --------------: | -------------------: | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | pp512 | 367.28 ± 1.88 | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | tg128 | 16.71 ± 0.03 |

J’ai donc supprimer le service de Tuxedo et fait une mise à jours : # apt-get autoremove. # systemctl stop tccd # systemctl disable tccd # ubuntu-drivers autoinstall En fait tccd fait l’installation de 560.35.05 et pas de 595.71.05.

L’export en Markdown ne fonctionne pas : # hermes sessions export --format md --older-than 90 --dry-run usage: hermes [-h] [--version] [-z PROMPT] [--usage-file PATH] [-m MODEL] [--provider PROVIDER] [-t TOOLSETS] [--resume SESSION] [--continue [SESSION_NAME]] [--worktree] [--accept-hooks] [--skills SKILLS] [--yolo] [--pass-session-id] [--ignore-user-config] [--ignore-rules] [--safe-mode] [--tui] [--cli] [--dev] {chat,model,moa,fallback,secrets,migrate,gateway,proxy,lsp,setup,postinstall,whatsapp,whatsapp-cloud,slack,send,login,logout,auth,status,cron,webhook,portal,kanban,project,hooks,doctor,security,dump,debug,backup,checkpoints,import,config,console,pairing,skills,bundles,plugins,curator,pets,journey,learning,memory-graph,memory,tools,computer-use,mcp,sessions,insights,claw,version,update,uninstall,acp,profile,completion,dashboard,serve,desktop,gui,logs,prompt-size} ... hermes: error: unrecognized arguments: --format --older-than 90 --dry-run