rdna4 repositories

Trending repositories tagged rdna4, ranked by trending score. Updated daily.

  1. 1
    NODIX-TECH/DLSS-5-MANAGER

    THE FIRST DLSS 5 MANAGER

    GitHub · F# · 1,642 stars · 78 forks · +18 stars in 24 hours · Trending score 2.45

  2. 2
    stew675/llama-cpp-rdna-boosts

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

    GitHub · Shell · 273 stars · 24 forks · +6 stars in 24 hours · Trending score 1.86

  3. 3
    IxMxAMAR/SageAttention-RDNA4

    Drop-in SageAttention for AMD RX 9070 / 9070 XT (RDNA4, gfx1201): custom HIP attention kernels for fp16 and bf16, 1.06-2.2x faster than PR #368's gfx12 port over the full call. Prebuilt Windows wheels; ComfyUI uses it through --use-sage-attention.

    GitHub · Python · 15 stars · 1 forks · +3 stars in 24 hours · Trending score 0.93

  4. 4
    zolotukhin/zinc

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

    GitHub · Zig · 532 stars · 39 forks · 0 stars in 24 hours · Trending score 0.73

  5. 5
    phantoslayer21/wronggpu

    Open-source (MIT) clean-room runtime for Model M upscaling and Ray Reconstruction on AMD Radeon RX 9000. Launcher sets up each game with OptiScaler. DirectX 12, Windows 10/11. Community project, pre-release.

    GitHub · C++ · 14 stars · 2 forks · 0 stars in 24 hours · Trending score 0.63

  6. 6
    countervolts/x4r

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

    GitHub · C++ · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.28

  7. 7
    OpenNeuralRendering/OpenRR

    Clean-room port of NVIDIA DLSS Ray Reconstruction for RDNA3/3.5/4 GPUs, for D3D12 and Vulkan games. MIT. https://ko-fi.com/proceduralnilo

    GitHub · C++ · 9 stars · 1 forks · 0 stars in 24 hours · Trending score 0.27

  8. 8
    tsaipifong/whirl-llm

    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.

    GitHub · C++ · 39 stars · 3 forks · 0 stars in 24 hours · Trending score 0.02

  9. 9
    GPUOpen-Tools/isa_spec_manager

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

    GitHub · C++ · 57 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    kr4ckhe4d/local-llm-benchmarks

    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.

    GitHub · Shell · 16 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    Dyluhn/R9V

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

    GitHub · Rust · 69 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    Heretek-AI/homebrew-tap

    ⚡ Zero-dependency Homebrew tap for high-performance LLMs (CachyLLama, ROCmFPX, llama-ai). Optimized for AMD ROCm 7 (Strix Halo, RDNA3/4), Apple Silicon Metal, & Vulkan RADV.

    GitHub · Ruby · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    parth-thakre/exl3-rdna4-recipe

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

    GitHub · Shell · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00