legacy-gpu

Here are 6 public repositories matching this topic...

h3rb3rn / ollama-legacy-gpu

Hardware-aware Ollama fork with legacy NVIDIA support, controllable runtime tuning, Q4/Q8 KV cache, Flash Attention, CUDA Graphs and optimized multi-GPU inference.

gpu tesla cuda inference self-hosted nvidia multi-gpu maxwell gpu-optimization llm llama-cpp flash-attention ollama ai-infrastructure legacy-gpu cuda-graphs

Updated Oct 9, 2026
Python

earldodd / nvidia-390-kernel68-patches

Star

Fix NVIDIA 390.157 DKMS build failures and Xorg crash on kernel 6.8 / Ubuntu 24.04 / Linux Mint 22

ubuntu xorg linux-kernel nvidia linux-mint dkms fermi nvidia-390 legacy-gpu kernel-6-8

Updated May 25, 2026

sanchez314c / ollama

Sponsor

Star

Ollama with PARAMETER think support + CUDA 3.5/3.7 (Tesla K80) + ROCm gfx803 (RX 580) legacy GPU support

Updated May 15, 2026
Go

spivanatalie64 / acreetionos-gdm-es1000

Star

GDM + GNOME configuration patches for AMD/ATI ES1000 (R100) GPUs — making the login screen usable on legacy hardware

xorg gnome gdm display-manager radeon legacy-gpu acreetionos es1000

Updated Jul 4, 2026
Shell

Yew1o1 / sunshine-maxwell

Star

Patched Sunshine fork with NVENC support for 1st/2nd generation NVIDIA NVENC GPUs, including Maxwell (GTX 900 series).

nvidia sunshine maxwell nvenc legacy-gpu gtx-900

Updated Sep 27, 2026
C++

jsfan3 / remove-ai-watermarks-low-vram

Star

Unofficial low-VRAM fork of wiltodelta/remove-ai-watermarks for legacy NVIDIA GPUs with 4 GB VRAM, face-free processing, and OCR-guided text restoration.

Updated Oct 6, 2026
Python

Add this topic to your repo

To associate your repository with the legacy-gpu topic, visit your repo's landing page and select "manage topics."

Learn more