NodeBB

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]

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}"

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

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

Les logs avant le build : # export LD_LIBRARY_PATH=/usr/local/cuda/lib # export PATH=$PATH:/usr/local/cuda/bin # cmake .. -DGGML_CUDA=ON CMAKE_BUILD_TYPE=Release -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with GGML_CCACHE=OFF -- CMAKE_SYSTEM_PROCESSOR: x86_64 -- GGML_SYSTEM_ARCH: x86 -- Including CPU backend -- x86 detected -- Adding CPU backend variant ggml-cpu: -march=native -- CUDA Toolkit found -- Using CMAKE_CUDA_ARCHITECTURES=75-virtual;80-virtual;86-real;89-real;90-virtual;120a-real;121a-real CMAKE_CUDA_ARCHITECTURES_NATIVE= -- CUDA host compiler is GNU 11.4.0 -- Including CUDA backend -- ggml version: 0.15.1 -- ggml commit: b4024af6c -- OpenSSL found: 3.0.2 -- Generating embedded license file for target: llama-app -- Configuring done -- Generating done -- Build files have been written to: /home/XXXX/GIT/llama.cpp/build

Pendant l’utilisation : # nvidia-smi Tue Jun 30 12:35:32 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 55C P0 28W / 115W | 4621MiB / 6144MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1820494 G /usr/lib/xorg/Xorg 4MiB | | 0 N/A N/A 1845119 C /usr/local/bin/llama-server 4598MiB | +-----------------------------------------------------------------------------------------+

Après la mise à jours des modèles : # ollama list NAME ID SIZE MODIFIED gpt-oss:20b 17052f91a42e 13 GB About a minute ago llama2:latest 78e26419b446 3.8 GB 18 minutes ago phi4:latest ac896e5b8b34 9.1 GB 18 minutes ago qwen2:latest dd314f039b9d 4.4 GB 18 minutes ago gemma2:latest ff02c3702f32 5.4 GB 18 minutes ago mistral:latest 6577803aa9a0 4.4 GB 18 minutes ago llama3.1:latest 46e0c10c039e 4.9 GB 22 minutes ago llava:latest 8dd30f6b0cb1 4.7 GB 22 minutes ago llava:13b 0d0eb4d7f485 8.0 GB 16 months ago llava:7b 8dd30f6b0cb1 4.7 GB 16 months ago llama3.1:8b 46e0c10c039e 4.9 GB 16 months ago mistral:7b f974a74358d6 4.1 GB 16 months ago gemma2:9b ff02c3702f32 5.4 GB 16 months ago qwen2:7b dd314f039b9d 4.4 GB 16 months ago phi4:14b ac896e5b8b34 9.1 GB 16 months ago

Nouveau test : # du -sh /var/cache/uptrack/* 4.0K /var/cache/uptrack/backoff 4.0K /var/cache/uptrack/backoff-counter 2.5G /var/cache/uptrack/Linux 4.0K /var/cache/uptrack/status # uptrack-uname -r 5.4.17-2136.349.3.1.el8uek.x86_64 # uptrack-show Installed updates: None # du -sh /var/cache/uptrack/Linux/x86_64/* 426M /var/cache/uptrack/Linux/x86_64/5.4.17-2102.201.3.el8uek.x86_64 287M /var/cache/uptrack/Linux/x86_64/5.4.17-2136.316.7.el8uek.x86_64 287M /var/cache/uptrack/Linux/x86_64/5.4.17-2136.324.5.3.el8uek.x86_64 456M /var/cache/uptrack/Linux/x86_64/5.4.17-2136.331.7.el8uek.x86_64 270M /var/cache/uptrack/Linux/x86_64/5.4.17-2136.336.5.1.el8uek.x86_64 604M /var/cache/uptrack/Linux/x86_64/5.4.17-2136.337.5.1.el8uek.x86_64 170M /var/cache/uptrack/Linux/x86_64/5.4.17-2136.349.3.1.el8uek.x86_64 # yum remove uptrack Dependencies resolved. ... # yum install uptrack Last metadata expiration check: 1:38:15 ago on Tue 12 May 2026 01:20:27 PM CEST. Dependencies resolved. ... # du -sh /var/cache/uptrack/ 0 /var/cache/uptrack/

La RAM est Samsung : # lshw -c memory | grep "product" product: M471A4G43AB1-CWE product: M471A4G43AB1-CWE Samsung M471A4G43AB1-CWE - 32 Go - 1 x 32 Go - DDR4-3200 MHz - 260-pin So-DIMM (M471A4G43AB1-CWE)