Arduino library for INA226 power sensor

Pre-built wheels for llama-cpp-python across platforms and CUDA versions

Ampere optimized llama.cpp

Cross-platform FlashAttention-2 Triton implementation for Turing+ GPUs with custom configuration mode

AML's goal is to make benchmarking of various AI architectures on Ampere CPUs a pleasurable experience :)

Setup instructions for running Valheim on Oracle Cloud Infrastructure using Arm also available at https://codeberg.org/husjon/valheim_server_oci_setup

Arduino energy monitor, using SCT-013-030 current sensors

Production-grade runtime patches for vLLM (45+ patches) — Qwen3.6-35B-A3B-FP8 hybrid GDN+MoE on NVIDIA Ampere (SM 80-86). 127 tok/s MTP free-form, 99 tok/s suffix tool-call (max 175). TurboQuant k8v4 KV cache, 256K context verified to 252K. P67 multi-query kernel + Suffix Decoding + adaptive ngram K. Zero source modifications.

First public benchmark of llama.cpp speculative decoding on Qwen3.6-35B-A3B with a single RTX 3090 (post PR #19493 merge, 2026-04-19). 19 configurations covering ngram-cache, ngram-mod, and classic draft with vocab-matched Qwen3.5-0.8B. Finding: no variant achieves net speedup on Ampere + A3B MoE. Raw JSON, plots, full reproducibility.

We are a fosshost project which is delivering ARM-based hardware into multiple, global data centers. We document and keep a diary of our project daily.

Validated Gemma4 GPTQ on Ampere (RTX 3090/3060) — Marlin JIT nvcc compatibility fixes included

Terraform to provision an OCI OKE cluster on Ampere A1 Processors, and then deploy nginx on it

Single Yocto layer for all Ampere Altra Arm 64-bit based Computer on Modules (COM-HPC). This layer has the support for the following products AADP, AADK, AADR, AVA

Deploy a complete, self-hosted AI stack for private LLMs, agentic workflows, and content generation. One-command Docker Compose deployment on any cloud.

🔌 A PowerShell Cmdlet library powered by Ampere

📦 A fully automated method for installing Nvidia drivers on Arch Linux

How to deploy Ampere Altra Arm–based processors on Azure for Azure Virtual Machines and Azure Kubernetes Service

Minimal GPU runtime for Python - high-performance CUDA kernels, memory management, and LLM inference without heavy dependencies

A VR application to help you understand the seven fundamental units in physics. And more...

16-step CUDA optimization of FlashAttention-2 achieving 99.2% of official performance on A100 — Ampere architecture