rdna4

THE FIRST DLSS 5 MANAGER

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 ]

A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance

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

Shape-specialized ROCm inference for Qwen3.8 Flash Next on RDNA4

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

WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Ryzen AI Max+ 395 (Radeon 8060S) and Radeon AI PRO R9700. Unzip and run, only the AMD driver.

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

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

AMD Radeon 9700 AI PRO RDNA multi GPU Tools for llm/vLLM inference, tuning, overclocking, undervolting and LLM models benchmarking

Measured llama.cpp benchmarks on AMD Radeon RDNA4 with ROCm: RX 9070 XT + Radeon AI PRO R9700 (48 GB). Qwen3.8, Gemma 4, GLM, gpt-oss; GGUF quant quality (KLD), MTP speculative decoding, 128K context, Claude Code with local models.

Quantized attention for AMD RX 9070 / 9070 XT (RDNA4, gfx1201): a hand-written HIP attention kernel behind SageAttention, serving the fused q/k/v views video models send, at 0.87-0.94x PR #368's time over production sizes.

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。

vLLM for AMD RDNA4 (gfx1201): Radeon AI PRO R9700 & RX 9070 XT — native MXFP4 linear kernel + spec-decode verify fix, carried as rebased branches (fork-carry model)

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

Intel XeSS XMX kernels translated to run on AMD RDNA3/RDNA4 WMMA under Linux/Proton.

Qwen3.8-27B (EXL3) on an AMD RX 9070 XT: ~150 tok/s for code, 96k context, one-line install (container, any Linux distro)

Moved. See: https://github.com/RX4Darwin/AMDRadeonRDNA4.kext