skills.rest
ianbarber
ianbarberCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

strix-halo-setup

Configure PyTorch for AMD Strix Halo gfx1151 with ROCm and GTT memory.

7|2|Updated Oct 26, 2025
Search Tags:#PyTorch#LLM#AMD Strix Halo#ROCm#GTT memory#Ryzen AI#GPU setup
One-click install
npx skills add https://github.com/ianbarber/strix-halo-skills --skill strix-halo-setup
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: strix-halo-setup
Source: https://github.com/ianbarber/strix-halo-skills/tree/main/.claude/skills/strix-halo-setup
Command: npx skills add https://github.com/ianbarber/strix-halo-skills --skill strix-halo-setup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ROCm, PyTorch, Conda, Vulkan, and includes scripts (resource) and references (resource) components.

What problem does it solve?

AMD Strix Halo users face significant hurdles setting up PyTorch for AI workloads: official PyTorch builds don't work (causing "HIP error: invalid device function"), and default memory configurations limit GPU access to ~33GB, preventing the use of larger models. This skill automates the complex setup, fixes these critical software and hardware limitations, and unlocks your system's full potential for advanced AI.

Core Features & Use Cases

  • Optimized PyTorch Installation: Automatically installs community-built PyTorch versions specifically compatible with AMD Strix Halo (gfx1151), ensuring your GPU works correctly for compute operations.
  • Expanded GPU Memory Access: Configures GTT (Graphics Translation Table) to allow your GPU to access up to 113GB of system RAM, enabling you to run 30B+ parameter models in FP16.
  • Comprehensive System Setup: Verifies ROCm installation, user group permissions, and sets up a ready-to-use Conda environment with all necessary environment variables and test scripts.
  • Use Case: A machine learning engineer acquires a new AMD Strix Halo laptop and needs to quickly set up an environment to fine-tune a 30B parameter LLM. Instead of spending days debugging driver issues and memory limits, they use this skill to get a fully optimized, working environment in minutes, ready to deploy large models.

Quick Start

Configure my AMD Strix Halo system for PyTorch and large AI models.

Frequently Asked Questions about strix-halo-setup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix HIP errors when running PyTorch on AMD Strix Halo?▼

PyTorch HIP errors on Strix Halo (gfx1151) occur because official builds don't support this GPU. Install community-built PyTorch versions compatible with AMD Strix Halo and ROCm 6.4.4+, configure correct environment variables, and verify ROCm installation to resolve invalid device function errors and enable compute operations.

Can I run large language models on AMD Strix Halo with limited GPU memory?▼

Yes. By configuring GTT (Graphics Translation Table), your Strix Halo GPU can access up to 113GB of system RAM instead of the default ~33GB, enabling you to run 30B+ parameter models in FP16 precision on a single device.

What's the fastest way to set up PyTorch for AMD Strix Halo?▼

Automated setup verifies ROCm, installs compatible PyTorch builds, configures GTT memory expansion, sets user group permissions, and creates a ready-to-use Conda environment with test scripts—completing complex multi-step configuration in minutes instead of days.

Does ROCm 6.4.4 support AMD Strix Halo GPU compute?▼

ROCm 6.4.4 and later support Strix Halo (gfx1151) compute, but require correct PyTorch community builds and GTT configuration. Official PyTorch releases don't work; setup automation ensures compatibility and proper memory access.

What are the prerequisites before configuring PyTorch on Strix Halo?▼

ROCm 6.4.4+, Conda, Vulkan, and user group permissions are required. The setup verifies these dependencies, installs PyTorch community builds optimized for gfx1151, configures environment variables, and structures a working ML project with test validation.

Why does my AMD Strix Halo laptop limit GPU memory access to 33GB?▼

Default GPU memory configuration restricts GTT (Graphics Translation Table) access. Enabling GTT expansion allows your Strix Halo GPU to leverage up to 113GB of system RAM, removing the primary barrier to running larger language models locally.

Related Skills

Explore More Software Engineering Skills→
X-School-AcademyX-School-Academy
9

dev-swarm-python

Install uv and configure Python environments with virtual environments.

Official
Basic
ovachieverovachiever
52

quantizing-models-bitsandbytes

Quantize LLMs to 8-bit or 4-bit precision using BitsAndBytes.

Community
Advanced
Tianyi-Billy-MaTianyi-Billy-Ma

pytorch-lightning

Automate PyTorch training workflows with LightningModule, Trainer, and LightningDataModule.

Community
Advanced
nelohenriqnelohenriq
1

llama-cpp

Execute CPU-based LLM inference with GGUF quantization on non-NVIDIA hardware.

Community
Intermediate