Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

Windows-only version of ComfyUI which uses AMD's official ROCm and PyTorch libraries to get better performance with AMD GPUs. [auto-installation and popular performance enhancing packages like triton * sage-attention * flash-attention * bitsandbytes included ]

The intelligent OptiScaler installer Linux gamers needed. Automates FSR4, XeSS & DLSS configuration with GPU-optimized profiles for RDNA3/4, Arc & RTX cards.

Utilities for accessing AMD's Machine-Readable GPU ISA Specifications.

LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.

Windows tool to bypass AMD driver clock gating and unlock real GPU boost clocks (RDNA4)

Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

llama.cpp with native AMD RDNA4 (gfx1201) ROCm 7.11 support - 98.97 tok/s AI inference, competitive with RTX 4070 Ti, 32GB VRAM

Fine-tune your own LLM on an AMD Radeon GPU — the easy, tested way. QLoRA via ROCm on Windows/WSL2 & Linux, a worked Gemma-4 example, a reusable live training dashboard, and a smoke test that proves the loss falls.

让 MinerU 在 AMD 显卡上以 vLLM + hybrid-auto-engine 满血运行！ 本项目是对官方文档中 AMD/ROCm 生态支持的有效补充。针对 MinerU 3.x 提供了一套完整的 ROCm 7.x + PyTorch 2.11.0 + vLLM 源码编译与部署方案，解析质量与速度对标 NVIDIA 旗舰显卡。

RAM-Backed MCP Memory Architecture for Consumer LLM Inference — 900K token context on 16GB VRAM

AWQ/W4A16 quantization, benchmarking and public release of Polish LLMs (PLLuM, Bielik) on AMD RDNA 4 (ROCm + vLLM-native) — reproducible methodology and hardware-envelope studies.

Reproducible Docker + LiteLLM stack for running Qwen 3.6 27B with MTP on AMD RDNA4 (gfx1201). Verified on Radeon AI PRO R9700 32 GB. Built from llama.cpp PR #22673.

Ollama with ROCm 7 GPU acceleration for AMD RDNA 4 (RX 9070, RX 9070 XT, RX 9060 XT - gfx1201) on Windows 11

RNS8 explores exact integer matrix multiplication on AMD GPU matrix engines.

Real-time dynamic GPU undervolting tool for AMD Radeon RX 9070 XT (RDNA4) on Windows. Automatically switches voltage offsets based on live core clock via AMD's official ADLX SDK — no static slider limitations. Features GUI dashboard, CLI controller, crash logger with TDR detection, and full preset management.

Visualize and monitor ROCm-SMI data locally or remotely via REST API — a more convenient alternative to rocm-smi.

Fork of xenia-edge (has207/xenia-edge) with critical bug fixes: posix_spawn replaces fork+exec to avoid AppImage FUSE unmount race on Linux, in_process_title_relaunch takes precedence over GameMode, improved filesystem path resolution with proper XDG/AppImage support, full codebase audit with 30+ bug fixes across CPU/GPU/kernel/UI/Android.

Fixes and patches for NVlabs/nvdiffrast to support AMD ROCm 7.1 and Wave64 architectures (gfx1100, gfx1201).

Run PyTorch natively on Windows 11 with an AMD RX 9070 XT (RDNA4 / gfx1201) on stable ROCm 7.2.1 — no WSL2, no Linux, no ZLUDA. Exact pinned wheel URLs, runtime env vars, documented RDNA4 pitfalls (broken nightlies, no xformers/flash-attn/bitsandbytes), and real benchmarks for ComfyUI, SD, LLMs, RVC/TTS. Verified on one 9070 XT.