Skip to content
Change the repository type filter

All

    Repositories list

    • Optimize the performance of LLM inference engines by automatically tuning parameters for a specific model.
      TypeScript
      0100Updated Nov 7, 2025Nov 7, 2025
    • sglang

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      3.3k000Updated Nov 7, 2025Nov 7, 2025
    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      738000Updated Nov 4, 2025Nov 4, 2025
    • DeepEP

      Public
      DeepEP: an efficient expert-parallel communication library
      Cuda
      976000Updated Nov 3, 2025Nov 3, 2025
    • FlashMLA

      Public
      FlashMLA: Efficient Multi-head Latent Attention Kernels
      C++
      896200Updated Oct 29, 2025Oct 29, 2025
    • Fast and memory-efficient exact attention
      Python
      2.1k200Updated Oct 26, 2025Oct 26, 2025
    • Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
      Python
      0000Updated Oct 20, 2025Oct 20, 2025
    • 0400Updated Sep 23, 2025Sep 23, 2025
    • DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Python
      738000Updated Sep 15, 2025Sep 15, 2025
    • All Dify Plugins listed in Dify Marketplace, plus illustrated plugin examples.
      465000Updated Aug 27, 2025Aug 27, 2025
    • Python
      0000Updated Aug 27, 2025Aug 27, 2025
    • FlashMLA: Efficient MLA decoding kernels
      Cuda
      896000Updated Aug 21, 2025Aug 21, 2025
    • TypeScript
      1000Updated Aug 19, 2025Aug 19, 2025
    • The Model Context Protocol (MCP) server that provides seamless interaction with Novita AI platform resources
      JavaScript
      91203Updated May 12, 2025May 12, 2025
    • JavaScript SDK for Novita AI API (Txt2Img, Img2Img, Txt2Video, Img2Video, Doodle, Remove Background, Replace Object, Reimagine, Merge Faces, ControlNet, VAE, LoRA)
      TypeScript
      41640Updated Mar 4, 2025Mar 4, 2025
    • Python SDK for Novita AI API (Txt2Img, Img2Img, Txt2Video, Img2Video, Doodle, Remove Background, Replace Object, Reimagine, Merge Faces, ControlNet, VAE, LoRA)
      Python
      82601Updated Nov 8, 2024Nov 8, 2024
    • Unofficial Implementation of Animate Anyone by Novita AI
      Python
      6878360Updated May 31, 2024May 31, 2024
    • golang-sdk

      Public archive
      Golang SDK for Novita AI API (Txt2Img, Img2Img, ControlNet, VAE, LoRA)
      Go
      3400Updated Nov 21, 2023Nov 21, 2023
    • An extension for stable-diffusion-webui to remove any object.
      JavaScript
      2533041Updated Oct 24, 2023Oct 24, 2023
    • litelama

      Public
      lightweight LAMA inference wrapper
      Python
      32500Updated Sep 28, 2023Sep 28, 2023