sdli1995/dlssg_for_sm86

Here is a dlssg for RTX30 Series GPU

What it solves

This project enables NVIDIA DLSS Frame Generation (DLSS-G) and accelerated DLSS Super Resolution on older RTX 20 (Turing) and RTX 30 (Ampere) series graphics cards. It bypasses hardware-based restrictions that typically limit these features to newer RTX 40/50 series GPUs, allowing users to improve frame rates in supported D3D12 games.

How it works

It functions as a proxy DLL that intercepts calls between the game and NVIDIA's Streamline/NGX libraries. By rewriting the reported GPU architecture to the game, it tricks the software into enabling features like Frame Generation. It also includes optimized inference kernels that provide performance gains over the standard NVIDIA implementation, with configurable presets for balancing image quality and speed.

Who it’s for

This project is for PC gamers using RTX 20 or RTX 30 series GPUs who want to access advanced frame-generation technology in modern games that would otherwise restrict these features to newer hardware.

Highlights

  • Enables DLSS-G (Frame Generation) on RTX 20 and 30 series cards.
  • Provides INT8-accelerated Super Resolution for improved performance on older architectures.
  • Includes multiple optimization levels (Presets) to trade off between image quality and GPU overhead.
  • Supports optional Intel XeSS-FG as an alternative frame generation engine.
  • Allows for up to 6X frame generation in games that support Dynamic Multi Frame Generation.

Written about in

Related

  • Project
    ShyVortex/dlss-unlocked

    A tool to unlock DLSS 3 Frame Generation and Neural Rendering on NVIDIA RTX 20/30 series and Intel Arc GPUs in DirectX 12 games.

  • Project
    artur-graniszewski/DLSS-Enabler

    A tool that simulates DLSS Upscaling and Frame Generation on any DirectX 12 compatible GPU for games that natively support DLSS2 and DLSS3.

  • Project
    perseval-BLR/NeuralScreen

    NeuralScreen is a Windows‑only tool that applies NVIDIA’s DLSS 5 neural upscaling (and optional DLSS 4.5 frame generation) to the whole desktop or a single window in real‑time, offering sharper visuals and higher FPS for RTX 20‑series and newer GPUs.

  • Dispatch
    OpenDLSS-NR: Vulkan Reimplementation of NVIDIA DLSS 5 Neural Rendering (Bit‑Exact)

    OpenDLSS-NR is a Vulkan reimplementation of NVIDIA's DLSS 5 neural rendering network that achieves byte‑for‑byte parity with the original using FP8 tensor‑core kernels.

  • Project
    MiaAI-Lab/Qwen3.8-27B-SGLang-DGX-Spark

    A Docker‑based deployment kit for serving the 27‑billion‑parameter Qwen 3.8 model on NVIDIA DGX Spark using SGLang. Includes ready‑made scripts for three speculative decoding engines (EAGLE/MTP, DSpark, DFlash2), benchmark utilities, and easy configuration of context length (up to 1 M tokens), concurrency (up to 10), and quantisation. Designed for engineers who need high‑performance LLM inference on a‑arch64 GPU server.