8000 tdh-archive repositories · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

@tdh-archive tdh-archive

Change the repository type filter

All

    Repositories list

    21 repositories

    • distributed-llama

      Public
      Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
      C++
      •
      MIT License
      •146•0•0•0•Updated Apr 26, 2025Apr 26, 2025

    • x-transformers

      Public
      A concise but complete full-attention transformer with a set of promising experimental features from various papers
      Python
      •
      MIT License
      •456•0•0•0•Updated Apr 18, 2025Apr 18, 2025

    • DeepSeek-V3

      Public
      Python
      •
      MIT License
      •16k•0•0•0•Updated Apr 18, 2025Apr 18, 2025

    • prima.cpp

      Public
      prima.cpp: Speeding up 70B-scale LLM inference on low-resource everyday home clusters
      C++
      •
      MIT License
      •46•0•0•0•Updated Apr 17, 2025Apr 17, 2025

    • burn

      Public
      Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
      Rust
      •
      Apache License 2.0
      •569•0•0•0•Updated Mar 25, 2025Mar 25, 2025

    • native-sparse-attention-pytorch

      Public
      Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
      Python
      •
      MIT License
      •31•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • FlashMLA

      Public
      C++
      •
      MIT License
      •831•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      •
      MIT License
      •585•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • zstd

      Public
      Zstandard - Fast real-time compression algorithm
      C
      •
      Other
      •2.2k•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • exo

      Public
      Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
      Python
      •
      GNU General Public License v3.0
      •1.8k•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • NotepadNext

      Public
      A cross-platform, reimplementation of Notepad++
      C++
      •
      GNU General Public License v3.0
      •598•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • mflux

      Public
      A MLX port of FLUX based on the Huggingface Diffusers implementation.
      Python
      •
      MIT License
      •81•0•0•0•Updated Mar 15, 2025Mar 15, 2025

    • picotron

      Public
      Minimalistic 4D-parallelism distributed training framework for education purpose
      Python
      •
      Apache License 2.0
      •98•0•0•0•Updated Mar 7, 2025Mar 7, 2025

    • vit-pytorch

      Public
      Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
      Python
      •
      MIT License
      •3.3k•0•0•0•Updated Mar 5, 2025Mar 5, 2025

    • mamba.py

      Public
      A simple and efficient Mamba implementation in pure PyTorch and MLX.
      Python
      •
      MIT License
      •104•0•0•0•Updated Dec 4, 2024Dec 4, 2024

    • Lime3DS

      Public
      A 3DS emulator based on Citra
      C++
      •
      GNU General Public License v2.0
      •261•0•0•0•Updated Oct 30, 2024Oct 30, 2024

    • cake

      Public
      Distributed LLM and StableDiffusion inference for mobile, desktop and server.
      Rust
      •
      Other
      •164•0•0•0•Updated Oct 23, 2024Oct 23, 2024

    • grok-1

      Public
      Grok open release
      Python
      •
      Apache License 2.0
      •8.4k•0•0•0•Updated Aug 30, 2024Aug 30, 2024

    • fast_mamba.np

      Public
      A pure and fast NumPy implementation of Mamba with cache support.
      Python
      •
      MIT License
      •1•0•0•0•Updated Jun 16, 2024Jun 16, 2024

    • mlx-bitnet

      Public
      1.58 Bit LLM on Apple Silicon using MLX
      Python
      •24•0•0•0•Updated May 10, 2024May 10, 2024

    • candle

      Public
      Deep learning library implemented from scratch in numpy. Mixtral, Mamba, LLaMA, GPT, ResNet, and other experiments.
      Jupyter Notebook
      •4•0•0•0•Updated Apr 12, 2024Apr 12, 2024
    0