Guides
Step-by-step solutions for real problems. Every guide leads with the working answer, then explains the reasoning — and states exactly what it was tested on.
- Check Your GPU's Real PCIe Bandwidth on Linux
See what PCIe link width and generation your GPU actually negotiated (lspci vs nvidia-smi), what the numbers should be, and when a downgrade actually matters.
- Run MiniMax H3 Locally with Diffusers
MiniMax H3 generates video and audio together and needs two ~62 GB BF16 components. Run it on one high-memory GPU or split it across two 48 GB cards — Modular Diffusers, no ComfyUI.
- Install ROCm 7.14 on AMD Strix Halo / Ryzen AI Max+
Install and verify ROCm 7.14 with gfx1151 support on a Strix Halo (Ryzen AI Max+) laptop — repository, the amdrocm-core-dev package set, permissions, and rocminfo/HIP/llama.cpp verification.
- Run llama.cpp on AMD Strix Halo: ROCm and Vulkan Setup
Practical llama.cpp setup for Strix Halo (Ryzen AI Max+ / Radeon 8060S) — both backends (ROCm/HIP and Vulkan), which to pick, build commands, device selection, memory and large-context notes.
- Recommended llama.cpp Setup for Strix Halo
The starting point we recommend on AMD Strix Halo (Ryzen AI Max+ / Radeon 8060S) for llama.cpp: ROCm as the default backend, Vulkan as the fallback, and when MTP speculative decoding is worth enabling.
- RTX PRO 5000 Blackwell eGPU on Linux with Sonnet 850T5
Get an NVIDIA RTX PRO 5000 Blackwell working as a Thunderbolt 5 eGPU under Linux — the proven boot/hot-plug sequence, the Sonnet 850T5 PCIe topology, small-BAR behavior, every workaround and its sourcing, BIOS outcomes.
- Set Up Vulkan Compute on AMD Strix Halo / Radeon 8060S
Get Vulkan compute working on Strix Halo with the Mesa RADV driver — Kisak PPA setup, exact packages, vulkaninfo verification, and a llama.cpp Vulkan build.
- Build llama.cpp with CUDA for NVIDIA Blackwell
Compile llama.cpp for Blackwell GPUs (sm_120) with a current CUDA toolkit — correct architecture flags, build commands, and fixes for the errors you will actually hit.