Skip to content

Strix Halo ROCm Quick Start

Single-page path from bare Ubuntu 26.04 LTS to running LLMs on GPU with the AMD Ryzen AI Max+ 395 APU (gfx1151).

Tested Environment

Ubuntu 26.04 LTS ("Resolute Raccoon"), Linux 7.0 kernel, ROCm 7.1 (in-distro) or upstream 7.2.x, 128GB LPDDR5X-8000 quad-channel. For detailed configuration of individual components, see the linked pages throughout this guide.

1. Verify Kernel

Ubuntu 26.04 ships Linux 7.0 by default and the server installer auto-installs HWE/OEM metapackages where applicable, so no manual kernel install is needed for gfx1151. Confirm:

uname -r
# Should show 7.0.x or newer

AMD's official requirement for Ryzen AI Max (gfx1151) is kernel 6.18.4+ (mainline) or 6.17 HWE — Ubuntu 26.04's 7.0 kernel clears this.

2. Install ROCm 7.x

Option A: in-distro ROCm 7.1 (one command, fewest moving parts)

sudo apt update
sudo apt install rocm

Ubuntu 26.04 ships ROCm 7.1.0 in Universe. This is roughly one minor behind upstream's 7.2.x but receives Ubuntu security updates and avoids third-party repos.

Option B: upstream AMD repo (newer ROCm, faster cadence)

# AMD's resolute path may not be live yet at release; verify on repo.radeon.com first.
wget https://repo.radeon.com/amdgpu-install/latest/ubuntu/noble/amdgpu-install_7.1.1.70101-1_all.deb
sudo apt install ./amdgpu-install_7.1.1.70101-1_all.deb
sudo amdgpu-install --usecase=rocm,hip,opencl,graphics,dkms

Add your user to the required groups (either option):

sudo usermod -aG video,render $USER
newgrp video
newgrp render

3. Verify GPU Detection

rocminfo | grep gfx
# Should show: Name:                    gfx1151

rocm-smi
# Should show the AMD Radeon device with temperature, power, etc.

No HSA Override Needed

ROCm 7.x has native gfx1151 support. You do not need HSA_OVERRIDE_GFX_VERSION.

4. Allocate VRAM with amd-ttm

By default, the system allocates roughly 62GB as GPU-accessible memory. For large LLMs, allocate more using amd-debug-tools:

# Install amd-debug-tools
pipx install amd-debug-tools

# Check current allocation
amd-ttm
# Shows current GTT (Graphics Translation Table) size

# Set to 108GB (leaves ~20GB for OS)
amd-ttm --set 108
sudo reboot

Verify after reboot:

amd-ttm
# Should confirm ~108GB allocation

rocm-smi --showmeminfo vram
# Should reflect the new allocation

For more details on memory allocation strategies, see Memory Configuration.

5. Install and Test Ollama

curl -fsSL https://ollama.com/install.sh | sh

Run a test model:

ollama run llama3.2

Verify GPU usage:

ollama ps
# Should show GPU memory usage, not CPU

6. llama.cpp (Docker)

For llama.cpp via Docker with ROCm:

docker run -d \
  --device=/dev/kfd \
  --device=/dev/dri \
  --group-add video \
  --group-add render \
  -v /path/to/models:/models \
  -p 8080:8080 \
  ghcr.io/ggml-org/llama.cpp:server-rocm \
  -m /models/your-model.gguf \
  --host 0.0.0.0 \
  -ngl 99

See GPU Containers for Docker Compose examples.

Troubleshooting

GPU not detected by rocminfo

# Check amdgpu driver is loaded
lsmod | grep amdgpu

# If not loaded
sudo modprobe amdgpu

# Check for blacklist entries
grep -r amdgpu /etc/modprobe.d/
# Remove any blacklist lines if found

# Rebuild initramfs after changes
sudo update-initramfs -u
sudo reboot

Wrong kernel booting

# Check which kernels are installed
dpkg -l | grep linux-image

# Set the desired kernel as default (replace 7.0.x-N-generic with the actual entry)
sudo sed -i 's/GRUB_DEFAULT=.*/GRUB_DEFAULT="Advanced options for Ubuntu>Ubuntu, with Linux 7.0.0-N-generic"/' /etc/default/grub
sudo update-grub
sudo reboot

rocm-smi shows no devices

Ensure your user is in the video and render groups:

groups $USER
# Should include: video render

# If not, add and re-login
sudo usermod -aG video,render $USER
# Log out and back in

What's Next

Sources

This guide consolidates information from the following community resources: