00:15:11 Hello all - I am trying to make a Intel Arc B70 card to work in FreeBSD 15.1 - I want to use it with llama.cpp to serve llms --- I have a problem, I installed drm-kmod , gpu-firmware-intel-kmod-battlemage and enable in /etc/rc.conf kld_list="i915kms" ( though I understand that battle image is not 1915kms) ---- I wonder if anyone can hint what to do, how to test it - nvtop tells me no GPU to load... 00:16:57 it seem that it is an intel xe driver... 00:48:57 It seem that people are working on it since 2024 https://github.com/freebsd/drm-kmod/issues/316 00:50:04 mary751: I think it's kind of impossible to use Nvidia's API (CUDA) on Intel's GPU cards. 00:52:16 checkpoint, obviously - maybe I misstype something - I wonder how should I configure Vulkan 01:00:59 mary751: have you tried installing latest drm-kmod driver (pkg install drm-kmod-20260508) ? 01:04:41 checkpoint, yes - I install it - i wonder if in /etc/rc.conf I need to add kld_list="i915kms" ? or xe --- or what ? 01:06:48 mary751: try "kldload i915kms" as root and see if that detects your GPU card. 01:12:09 mary751: frankly, I don't know much about Vulkan on FreeBSD, try readinig these forum discussions: https://forums.freebsd.org/tags/vulkan/, seems some ppl were ably to run wisper models. 01:14:00 you can use vulkan with nvidia driver to run a local LLM on a nvidia GPU. But you're probably better offer buying a box dedicated to it like a DGX Spark. 01:14:35 anything worthwhile requires at least 200GB 01:15:43 bsdroberts: pls define "worthwhile" ? :) 01:17:08 if you want to be able to run a open weight flash model and essentially replace the role a cloud provider has. 01:36:25 Actually I am running FreeBSD 15.1 llama.cpp with qwen 3.6 and 3.7 very well or RTX NVIDIA cards --- Intel Arc B70 with 32G is only $1200 --- that is why I am trying to use it... 01:36:56 Qwen 3.6 and Qwen 3.7 are absolutely phenomenal 01:51:33 * checkpoint has just built and tested whisper.cpp with Vulkan support on FreeBSD, it works. 01:52:05 checkpoint, can you share the steps -- I was planing to do this 01:52:37 cmake -B build -DGGML_VULKAN=1 01:52:38 cmake --build build --config Release 01:52:44 that's all I did 01:53:17 OK, but about whisper, how do you install and configure it ? 01:53:29 I have two GPUs on my laptop: nvidia and amdgpu, both detected and used. 01:53:32 Can you use your microphone and get it to the text 01:54:13 mary751: yes works fine and very quickly 01:54:58 once build it complete, just run it: ./build/bin/whisper-stream -l ru -m models/ggml-small.bin 01:55:21 or -l 01:57:49 I think you should make a video - step by step --- would be of great use 02:12:28 stangely whisper.cpp builds flowlessly on my laptop (FreeBSD 13.5), but fails with error "Could NOT find Vulkan (missing: glslc)" on another machine with same AMDGPU but with FreeBSD 15.1. 02:13:32 looks like some package (library) is missing, but which one ?