Search results for query: nvidia

  1. Alain De Vos

    Nvidia 595.99.02 is better !

    For me, x@myfreebsd:/SSD/home/x $ pkg info |egrep "nvidia|drm" drm-612-kmod-6.12.85.1501000_1 Direct Rendering Manager (DRM) GPU drivers libdrm-2.4.133,1 Direct Rendering Manager library and headers nvidia-driver-595.84 NVIDIA graphics driver userland...
  2. drsnx60

    Nvidia 595.99.02 is better !

    Status-Report : Nvidia driver 595:99.02.150102 appears to be more stable than its predessesor 595.91 . With 595.91 I had kernel panics when trying to use DRM-612. With 595.99 DRM-612 starts and works again. ( using a desktop based on i7-11700K...
  3. T

    nvidia and GeForce 3060 on FreeBSD 14.4 - not a happy experience

    I finally got around to rebuild the relevant *kmods from ports Sep 9 20:43:46 kg-core2 pkg-static[36888]: nvidia-kmod-595.84.1404000 deinstalled Sep 9 20:43:48 kg-core2 pkg-static[36988]: nvidia-kmod-595.84.1404000 installed Sep 9 20:48:01 kg-core2 pkg-static[38415]...
  4. G

    general/other Cuda working on Freebsd using Podman - support thread

    nvidia-smi Wed Sep 9 20:07:50 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 595.84 Driver Version: 595.99.02 CUDA Version: 13.2 |...
  5. G

    general/other Cuda working on Freebsd using Podman - support thread

    Well, I figured the easiest way would be to upgrade the linux-nvidia-libs to 595.99.02 since FreeBSD Ports Search lists it. However after doing the below I am confused. git pull git status On branch main Your branch is up to date with 'origin/main'. ls x11/linux-nvidia-libs*...
  6. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    looks like you have a mismatch between the driver version and the libraries you could try updating and reinstalling the drivers maybe something like this sudo pkg update sudo pkg upgrade linux-nvidia-libs nvidia-driver and rebooting
  7. G

    general/other Cuda working on Freebsd using Podman - support thread

    Now it gets interesting. pkg info | grep nvidia linux-nvidia-libs-595.84 NVIDIA graphics libraries and programs (Linux) nvidia-driver-595.99.02 NVIDIA graphics driver userland nvidia-drm-612-kmod-595.99.02.1501000 NVIDIA DRM Kernel Module nvidia-drm-kmod-595.99.02 NVIDIA DRM...
  8. G

    general/other Cuda working on Freebsd using Podman - support thread

    No, it's in the container. I have rebuilt base x11 and ollama but still same. Logs now say this: sudo podman-compose logs -f chmod: changing permissions of '/run/user/1001-writeable': Operation not permitted chown: cannot read directory '/run/user/1001-writeable': Permission denied /grandpa
  9. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    is that nvidia-smi output on the freebsd side if you google "freebsd NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver." there are some hits the first one for freebsd...
  10. G

    general/other Cuda working on Freebsd using Podman - support thread

    I did sudo pkg install x11/linux-nvidia-libs and that gave this output from nvidia-smi so small step forward. Still no cuda in ollama though. Maybe rebuild base? bash-5.1$ nvidia-smi NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA...
  11. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    what are the permission on /dev/nvidia ls -l /dev/nvidia* the devfs.rules change the permissions to this crw-rw---- 1 root video 0xad 9 Sep 11:53 /dev/nvidia-modeset crw-rw---- 1 root video 0xab 9 Sep 11:53 /dev/nvidia0 crw-rw---- 1 root video 0xac 9 Sep 11:53 /dev/nvidiactl and the...
  12. G

    general/other Cuda working on Freebsd using Podman - support thread

    ...video add path 'drm/*' mode 0660 group video add path 'input/*' mode 0660 group video add path 'input/event*' mode 0660 group video add path 'nvidia*' mode 0660 group video [devfsrules_jail=4] add include $devfsrules_unhide_basic add include $devfsrules_unhide_login add path 'mixer*' unhide...
  13. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    ...video add path 'drm/*' mode 0660 group video add path 'input/*' mode 0660 group video add path 'input/event*' mode 0660 group video add path 'nvidia*' mode 0660 group video [devfsrules_jail=4] add include $devfsrules_unhide_basic add include $devfsrules_unhide_login add path 'mixer*' unhide...
  14. G

    general/other Cuda working on Freebsd using Podman - support thread

    ...line jail_devfs_ruleset="5" in /usr/local/etc/containers/container.conf and changed /etc/devfs.rules to your default but still get bash-5.1$ nvidia-smi bash: nvidia-smi: command not found Mind you - I have NOT added devfs_system_ruleset="localrules" to /etc/rc.conf because if I do this pc...
  15. DanielBowman

    Technical aspects of running local LLMs on FreeBSD

    BSD Jedi has some Ollama tutorial and a new one with a plug for some budget option cloud models. I run 16GB vRAM nvidia on Debian Linux Ollama - rarely used, mainly as brain for Home Assistant....for fun. I have good experience with Mixture of Experts models - gemma4. They really seem to use...
  16. G

    general/other Cuda working on Freebsd using Podman - support thread

    ...add path 'dri*' unhide add path 'dri/*' mode 0660 group video add path 'drm*' unhide add path 'drm/*' mode 0660 group video add path 'nvidia*' unhide add path 'nvidia*' mode 0660 group video add path 'input/*' mode 0660 group video add path 'input/event*' mode 0660 group video add path...
  17. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    that rules those out then bash: nvidia-smi: command not found looks like a devfs issue you seem to be missing this in devfs.rules [devfsrules_jail=4] add include $devfsrules_unhide_basic add include $devfsrules_unhide_login add path 'mixer*' unhide add path 'dsp*' unhide add path 'dri*'...
  18. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    Tested in a Rocky Linux Podman container and it works bash-5.1$ ./hello-world-cuda2 Using device: NVIDIA GeForce GTX 1650 Hello, World! from thread 4 (block 1, thread 0) Hello, World! from thread 5 (block 1, thread 1) Hello, World! from thread 6 (block 1, thread 2) Hello, World! from thread 7...
  19. G

    general/other Cuda working on Freebsd using Podman - support thread

    ...no_proxy:]" sudo podman exec -it -u ${USER} ollama /bin/bash bash-5.1$ ollama run llama3.1:8b >>> Send a message (/? for help) bash-5.1$ nvidia-smi bash: nvidia-smi: command not found On the BSD side: nvidia-smi Wed Sep 9 16:36:47 2026...
  20. NapoleonWils0n

    general/other Cuda working on Freebsd using Podman - support thread

    ...or tmux pane enter the container again cd ~/podman/freebsd-cuda/containers/ai/ollama sudo podman exec -it -u ${USER} ollama /bin/bash run nvidia-smi nvidia-smi the output should look like this bash-5.1$ nvidia-smi Wed Sep 9 12:09:42 2026...
Back
Top