NodeBB

Mise à jours de Ollama : # curl -fsSL https://ollama.com/install.sh | sh >>> Cleaning up old version at /usr/local/lib/ollama >>> Installing ollama to /usr/local >>> Downloading ollama-linux-amd64.tar.zst ######################################################################## 100.0% >>> Adding ollama user to render group... >>> Adding ollama user to video group... >>> Adding current user to ollama group... >>> Creating ollama systemd service... >>> Enabling and starting ollama service... >>> NVIDIA GPU installed. Visiblement même problème : ... juin 19 10:51:37 ollama[2964]: time=2026-06-19T10:51:37.153Z level=INFO source=model_list_cache.go:111 msg="model list cache hydration complete" models=16 failures=0 elapsed=654.370427ms juin 19 10:51:42 ollama[2964]: time=2026-06-19T10:51:42.591Z level=WARN source=cuda_compat.go:38 msg="NVIDIA driver too old" device="Quadro M5000" compute=5.2 driver=535 required_driver="570 or newer" juin 19 10:51:42 ollama[2964]: time=2026-06-19T10:51:42.591Z level=WARN source=cuda_compat.go:38 msg="NVIDIA driver too old" device="Quadro M4000" compute=5.2 driver=535 required_driver="570 or newer" juin 19 10:51:43 ollama[2964]: time=2026-06-19T10:51:43.181Z level=INFO source=types.go:32 msg="inference compute" id=1 filter_id=1 library=Vulkan compute=0.0 name=Vulkan1 description="Quadro M4000" libd> juin 19 10:51:43 ollama[2964]: time=2026-06-19T10:51:43.181Z level=INFO source=types.go:32 msg="inference compute" id=0 filter_id=0 library=Vulkan compute=0.0 name=Vulkan0 description="Quadro M5000" libd> ...

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

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

Modification de opcache /etc/php/8.2/cli/php.ini ; The amount of memory for interned strings in Mbytes. ;opcache.interned_strings_buffer=8 Après : ; The amount of memory for interned strings in Mbytes. opcache.interned_strings_buffer=16 Lancement de apache : # systemctl restart apache2

Nouvelle optimisation : # du -sh /etc/pve/firewall/cluster.fw 103K /etc/pve/firewall/cluster.fw # wc -l /etc/pve/firewall/cluster.fw 23780 /etc/pve/firewall/cluster.fw

J’ai du mal à voir : # /usr/sbin/parted -l Model: ATA QEMU HARDDISK (scsi) Disk /dev/sda: 64,4GB Sector size (logical/physical): 512B/512B Partition Table: loop Disk Flags: Number Start End Size File system Flags 1 0,00B 64,4GB 64,4GB ext4 Model: ATA QEMU HARDDISK (scsi) Disk /dev/sdb: 85,9GB Sector size (logical/physical): 512B/512B Partition Table: msdos Disk Flags: Number Start End Size Type File system Flags 1 1049kB 63,4GB 63,4GB primary ext4 boot 2 63,4GB 64,4GB 1022MB extended 5 63,4GB 64,4GB 1022MB logical linux-swap(v1) swap

Update : alpine-forgejo:~# apk update v3.23.4-222-g6275d971a54 [http://dl-cdn.alpinelinux.org/alpine/latest-stable/main] v3.23.4-222-g6275d971a54 [http://dl-cdn.alpinelinux.org/alpine/latest-stable/community] OK: 27601 distinct packages available alpine-forgejo:~# apk upgrade (1/4) Upgrading git-lfs (3.7.0-r8 -> 3.7.0-r9) (2/4) Upgrading libldap (2.6.10-r0 -> 2.6.13-r0) (3/4) Upgrading forgejo (13.0.5-r3 -> 13.0.5-r4) Installing file to etc/forgejo/app.ini.apk-new (4/4) Upgrading forgejo-openrc (13.0.5-r3 -> 13.0.5-r4) Executing busybox-1.37.0-r30.trigger OK: 180.1 MiB in 138 packages alpine-forgejo:~# apk update v3.23.4-222-g6275d971a54 [http://dl-cdn.alpinelinux.org/alpine/latest-stable/main] v3.23.4-222-g6275d971a54 [http://dl-cdn.alpinelinux.org/alpine/latest-stable/community] OK: 27597 distinct packages available alpine-forgejo:~# apk upgrade OK: 180.1 MiB in 138 packages

Update v0.19.1 : https://github.com/open-wanderer/wanderer/releases/tag/v0.19.1

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/

https://technical.city/en/cpu/Xeon-E5-2450-v2-vs-Xeon-Gold-6254 “Xeon Gold 6254 outperforms Xeon E5-2450 v2 by a whopping 257% based on our aggregate benchmark results.” [image: image.png] Sur CPU BOGOMIPS : 159998.72 à 374460.48 j’ai 134.04 % et pas 257%.