Home-enthusiast's guide to fine-tuning 27B+ LLMs on AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — the patches and tuning to make Linux mainline + ROCm 7.13 nightly + PyTorch 2.11 + bitsandbytes + flash-linear-attention all work together for multi-day LoRA training with out-of-process eval orchestration.
☆26Jun 9, 2026Updated last month
Alternatives and similar repositories for strix-halo-llm-finetune-guide
Users that are interested in strix-halo-llm-finetune-guide are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-strea…☆50May 10, 2026Updated 2 months ago
- ☆17Jul 21, 2026Updated last week
- ☆56Updated this week
- AMD Strix Halo / Ryzen AI Halo local LLM setup and benchmark guide for Ryzen AI MAX+ 395 and Radeon 8060S: Ollama, llama.cpp Vulkan/RADV,…☆255Updated this week
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆65Jul 10, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆62Updated this week
- LLM inference in C/C++☆124Updated this week
- NEW ROCmfp4 format for llama.cpp☆139Jun 13, 2026Updated last month
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆56Jul 7, 2026Updated 3 weeks ago
- ☆1,802Updated this week
- ROCm/AMD GPU benchmark suite for llama.cpp, whisper.cpp, PyTorch☆19Feb 4, 2026Updated 5 months ago
- ☆55Updated this week
- ☆145May 29, 2026Updated 2 months ago
- DGX Spark research and tests - containers, benchmarks, and investigation notes for running models on GB10 (SM 12.1)☆19Jul 19, 2026Updated 2 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Fully local, persona-driven AI companion bot for Telegram (Telethon) with optional Discord bridge. Modular text pipeline, per-user memory…☆17Jun 21, 2026Updated last month
- Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration☆636Updated this week
- ☆487Updated this week
- Ameoba Single key PCB variant designed for simplicity☆13Apr 17, 2023Updated 3 years ago
- Tensor library for machine learning☆36Updated this week
- A Void based Nomad cluster☆17Sep 24, 2025Updated 10 months ago
- ☆57Updated this week
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆62Updated this week
- Trackpoint emulator: 3 choc swithes and analog stick☆13Mar 23, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Constructive Solid Geometry (CSG) and Quick Hull Library for golang☆10Oct 30, 2019Updated 6 years ago
- The Operator Pattern, in Nomad☆17Nov 22, 2021Updated 4 years ago
- ☆19Mar 21, 2026Updated 4 months ago
- ☆10Feb 14, 2024Updated 2 years ago
- Project Code for "Scaling Infrastructure as Code: Proven Strategies and Productive Workflows" at Google Next '24☆12Apr 7, 2024Updated 2 years ago
- MCP that makes Xcode 26.3's MCP compatible with Cursor and other strict MCP-spec-compliant clients☆20Jul 2, 2026Updated last month
- Rest AIP server for commuticate with Tion devices☆12Dec 19, 2020Updated 5 years ago
- interact with your Kubernetes pods, retrieve information about pods, and receive expert insights and recommendations from gpt☆18Mar 26, 2024Updated 2 years ago
- Tencent Hunyuan 3 (295B MoE) on 2x NVIDIA DGX Spark: NVFP4 W4A16 + native MTP speculative decoding. First published MTP-on-GB10 numbers, …☆20Jul 13, 2026Updated 3 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- netactuator is an active network management tool, for graphing individual host activities and make individual host behavior patterns.☆16Jul 17, 2011Updated 15 years ago
- Deterministic Linux runtime enforcement with eBPF LSM: block file/network operations before syscalls complete.☆18Updated this week
- 🦉 OpenCode skill — error reflection & 5-Why root-cause learning agent☆17Jul 2, 2026Updated last month
- [Accepted to SOSP 2026] Fast Deterministic LLM Inference☆22Jul 24, 2026Updated last week
- An Intellij IDEA and Android Studio Plugin to de-obfuscate your Proguard stack traces☆16Jul 17, 2026Updated 2 weeks ago
- Share your content of clipboard between 2 computers!☆10Apr 3, 2018Updated 8 years ago
- ☆18Feb 2, 2022Updated 4 years ago