Tutorials

Do the work on a real box

Install ROCm 10.1 the documented way (one method, never mixed with Ubuntu archive `rocm`), prove gfx1201, run official Qwen instruct on llama.cpp, then expose a loopback /v1. vLLM is advanced. Confirm package names against AMD docs and the weekly card before you copy them.

1. 01 · starter · 40 min

   Install ROCm on a home Linux box

   ROCm 10.1.0 on a Radeon AI PRO R9700 — official Ubuntu 26.04.1 / 24.04.5 / 22.04.5 rows, ROCm CLI v0.2.0, and a do-not-mix-apt decision tree.

2. 02 · starter · 20 min

   Verify GPU and ROCm

   Prove the R9700 is visible, that HIP works, and that PyTorch is using the card — before you download a 20 GB model.

3. 03 · starter · 40 min

   Run a local Qwen (llama.cpp)

   Build llama.cpp first — Vulkan is the daily-driver path on our rig, HIP if rocminfo is clean — then run official Qwen instruct.

4. 04 · intermediate · 35 min

   Serve Qwen on the R9700

   Official Qwen instruct on a loopback /v1 — llama-server first, Strata for Flash, vLLM only in Advanced.