multi-gpu repositories

Trending repositories tagged multi-gpu, ranked by trending score. Updated daily.

  1. 1
    DevDock-AI/Speedy

    Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Strata.

    GitHub · C++ · 125 stars · 8 forks · +26 stars in 24 hours · Trending score 2.59

  2. 2
    Lowaltitudeflight/local-llm-tuning-guide

    A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decoding, KV cache. Every conclusion carries its evidence grade and reproducible conditions.

    GitHub · Python · 105 stars · 0 forks · 0 stars in 24 hours · Trending score 0.72

  3. 3
    FZJ-JSC/tutorial-multi-gpu

    Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial

    GitHub · C++ · 387 stars · 86 forks · 0 stars in 24 hours · Trending score 0.44

  4. 4
    projectchrono/DEM-Engine

    A dual-GPU DEM solver with complex grain geometry support

    GitHub · C++ · 136 stars · 34 forks · 0 stars in 24 hours · Trending score 0.42

  5. 5
    tobocop2/lilbee

    A local model engine with a search engine and web crawler built in. Run your coding agents on your own GPUs, and get cited answers from your files, code, and the sites you crawl. One executable.

    GitHub · Python · 71 stars · 9 forks · 0 stars in 24 hours · Trending score 0.36

  6. 6
    Shamrock-code/Shamrock

    The Shamrock Framework, an open-source, multi-GPU hydrodynamics framework for astrophysics. Scales seamlessly from laptops to exascale supercomputers, supporting SPH, AMR, and more.

    GitHub · C++ · 69 stars · 39 forks · 0 stars in 24 hours · Trending score 0.18

  7. 7
    Artain-AI/ignite-ms

    Fast self-hosted embedding engine for search, RAG, and reindexing workloads on NVIDIA GPUs. Built in Rust + TensorRT for teams that care about scale, cost, and control.

    GitHub · Rust · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.14

  8. 8
    defilantech/LLMKube

    Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

    GitHub · Go · 266 stars · 46 forks · −1 stars in 24 hours · Trending score 0.10

  9. 9
    mxxm-t/llmx

    C++ LLM inference runtime built from scratch, with CPU and Vulkan backends, GGUF support, and multi-GPU serving.

    GitHub · C++ · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.10

  10. 10
    Lumi-supercomputer/LUMI-AI-Guide

    The LUMI AI Guide is designed to assist users in migrating their machine learning applications from smaller-scale computing environments to the LUMI supercomputer.

    GitHub · Python · 84 stars · 20 forks · 0 stars in 24 hours · Trending score 0.08

  11. 11
    Cedriceuh/freetoken-rdna3

    Fast local LLM inference on AMD Radeon RX 7900 XTX / XT (RDNA3, ROCm): big Mixture-of-Experts models like Qwen3.8-Flash-Next on one or two consumer GPUs. Up to 4 parallel agents with 262k context each, or one 1M-token context, OpenAI/Anthropic API, NVFP4 and EXL3 checkpoints. A tuned build of FreeToken.

    GitHub · Python · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07

  12. 12
    surya-koritala/Glyd

    Lossless compression for LLM weights and KV cache, and the inference engine that runs on it.

    GitHub · Rust · 187 stars · 2 forks · −134 stars in 24 hours · Trending score 0.07

  13. 13
    lattice/quda

    QUDA is a library for performing calculations in lattice QCD on GPUs.

    GitHub · C++ · 370 stars · 125 forks · 0 stars in 24 hours · Trending score 0.03

  14. 14
    helmholtz-analytics/heat

    Distributed tensors and Machine Learning framework with GPU and MPI acceleration in Python

    GitHub · Python · 253 stars · 73 forks · 0 stars in 24 hours · Trending score 0.03

  15. 15
    WyvernTKC/llama.cpp-4xV100

    Fork of llama.cpp Nvida Volta V100 (tensor parallelism 4 x v100 GPU)

    GitHub · C++ · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  16. 16
    shootthesound/comfyui-mesh

    Split FLUX.2 and LTX 2.3 across two GPUs (LAN or same-machine) — NVENC compresses activations live on the wire. Icarus (ComfyUI node) + Daedalus (back-half server).

    GitHub · Python · 125 stars · 14 forks · 0 stars in 24 hours · Trending score 0.00

  17. 17
    attevon-llc/OpenTranscribe

    Self-hosted AI-powered transcription platform with speaker diarization, search, and collaboration features. Built with Svelte, FastAPI, and Docker for easy deployment.

    GitHub · Python · 106 stars · 26 forks · 0 stars in 24 hours · Trending score 0.00

  18. 18
    hainuo-wang/XReflection

    XReflection is a neat toolbox tailored for single-image reflection removal(SIRR). We offer state-of-the-art SIRR solutions for training and inference, with a high-performance data pipeline, multi-GPU/TPU/NPU support, and more!

    GitHub · Python · 56 stars · 9 forks · 0 stars in 24 hours · Trending score 0.00

  19. 19
    eth-cscs/ImplicitGlobalGrid.jl

    Almost trivial distributed parallelization of stencil-based GPU and CPU applications on a regular staggered grid

    GitHub · Julia · 205 stars · 24 forks · 0 stars in 24 hours · Trending score 0.00

  20. 20
    predsci/POT3D

    POT3D: High Performance Potential Field Solver

    GitHub · Fortran · 52 stars · 28 forks · 0 stars in 24 hours · Trending score 0.00

  21. 21
    aivrar/multi-turboquant

    Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simulation, Godzilla KVarN/TriAttention with SM86/SM89 qualification, CUDA weight sharing, and multi-GPU planning.

    GitHub · Python · 30 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00

  22. 22
    xero00000/expert-streaming-engine

    Bigger local AI on the PC you already own. Find models, chat locally, and run supported sparse models across SSD, RAM and NVIDIA GPUs with ESE Studio.

    GitHub · C++ · 20 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  23. 23
    zeroextub-collab/wisp

    Stream what shouldn't run.

    GitHub · Python · 9 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  24. 24
    sergey-automation/TurboPrefill

    Multi-GPU prefill acceleration for llama.cpp

    GitHub · C++ · 12 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00