Skip to content

@xlite-dev xlite-dev

Change the repository type filter

All

    Repositories list

    53 repositories

    • diffusers

      Public
      🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
      Python
      •
      Apache License 2.0
      •6.7k•0•0•0•Updated Jan 21, 2026Jan 21, 2026

    • sglang

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      •
      Apache License 2.0
      •4.1k•0•0•0•Updated Jan 20, 2026Jan 20, 2026

    • vllm-omni

      Public
      A framework for efficient model inference with omni-modality models
      Python
      •
      Apache License 2.0
      •308•0•0•0•Updated Jan 20, 2026Jan 20, 2026

    • ffpa-attn

      Public
      🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
      cudaattentionsdpamlamlsystensor-coresflash-attentiondeepseekdeepseek-v3deepseek-r1
      Cuda
      •
      GNU General Public License v3.0
      •13•246•1•0•Updated Jan 20, 2026Jan 20, 2026

    • cache-dit

      Public
      A Unified and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for 🤗DiTs.
      Python
      •
      Apache License 2.0
      •53•4•0•0•Updated Jan 19, 2026Jan 19, 2026

    • Awesome-DiT-Inference

      Public
      📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉
      fluxwandiffusionditsorastable-diffusionsdxlsd15deepcacheopen-sora-plan
      Python
      •
      GNU General Public License v3.0
      •25•500•0•0•Updated Jan 18, 2026Jan 18, 2026

    • Awesome-LLM-Inference

      Public
      📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
      mlavllmllm-inferenceawesome-llmflash-attentiontensorrt-llmpaged-attentiondeepseekflash-attention-3deepseek-v3
      Python
      •
      GNU General Public License v3.0
      •336•4.9k•0•0•Updated Jan 18, 2026Jan 18, 2026

    • lite.ai.toolkit

      Public
      🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉
      tensorrtmnnncnnonnxonnxruntimeyolov5tnnmnn-modelyoloxrobustvideomatting
      C++
      •
      GNU General Public License v3.0
      •770•4.4k•1•0•Updated Jan 18, 2026Jan 18, 2026

    • LeetCUDA

      Public
      📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
      cudacuda-kernelscuda-democuda-toolkitcuda-librarycuda-kernellearn-cudacuda-cpphgemmflash-attention
      Cuda
      •
      GNU General Public License v3.0
      •928•9.4k•1•0•Updated Jan 18, 2026Jan 18, 2026

    • flux-fast

      Public
      A forked version of flux-fast that makes flux-fast even faster with cache-dit.
      Python
      •16•4•0•0•Updated Jan 5, 2026Jan 5, 2026

    • Qwen-Image

      Public
      Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
      Python
      •
      Apache License 2.0
      •410•1•0•0•Updated Jan 1, 2026Jan 1, 2026

    • Z-Image

      Public
      Python
      •
      Apache License 2.0
      •565•1•0•0•Updated Dec 25, 2025Dec 25, 2025

    • SageAttention

      Public
      Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
      Cuda
      •
      Apache License 2.0
      •320•0•0•0•Updated Dec 3, 2025Dec 3, 2025

    • .github

      Public
      0•1•0•0•Updated Nov 25, 2025Nov 25, 2025

    • ImageReward

      Public
      [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
      Python
      •
      Apache License 2.0
      •83•0•0•0•Updated Oct 30, 2025Oct 30, 2025

    • longcat-video-fast

      Public
      🔥LongCat-Video 1.7x🎉 speedup: cache acceleration and 4/8-bits weight only.
      longcatlongcat-video
      Python
      •0•7•0•0•Updated Oct 28, 2025Oct 28, 2025

    • LongCat-Video

      Public
      Python
      •
      MIT License
      •270•0•0•0•Updated Oct 28, 2025Oct 28, 2025

    • ComfyUI

      Public
      The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
      Python
      •
      GNU General Public License v3.0
      •11k•0•0•0•Updated Oct 27, 2025Oct 27, 2025

    • qwen-image-fast

      Public
      ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs
      qwen-imageqwen-image-lightningqwen-image-editqwen-image-apiqwen-image-lora
      Python
      •
      Apache License 2.0
      •0•17•4•0•Updated Oct 24, 2025Oct 24, 2025

    • Kandinsky-5

      Public
      Kandinsky 5.0: A family of diffusion models for Video & Image generation
      Python
      •
      Apache License 2.0
      •49•0•0•0•Updated Oct 22, 2025Oct 22, 2025

    • Wan2.1

      Public
      Wan: Open and Advanced Large-Scale Video Generative Models
      Python
      •
      Apache License 2.0
      •2.3k•1•0•0•Updated Oct 17, 2025Oct 17, 2025

    • Wan2.2

      Public
      Wan: Open and Advanced Large-Scale Video Generative Models
      Python
      •
      Apache License 2.0
      •1.6k•0•0•0•Updated Oct 17, 2025Oct 17, 2025

    • nunchaku

      Public
      [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
      Python
      •
      Apache License 2.0
      •216•2•0•0•Updated Oct 15, 2025Oct 15, 2025

    • DiffSynth-Studio

      Public
      Enjoy the magic of Diffusion models!
      Python
      •
      Apache License 2.0
      •1.1k•0•0•0•Updated Oct 13, 2025Oct 13, 2025

    • HunyuanImage-3.0

      Public
      HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
      Python
      •
      Other
      •128•1•0•0•Updated Oct 4, 2025Oct 4, 2025

    • comfyui-cache-dit

      Public
      cache-dit for comfyui
      Python
      •4•31•3•0•Updated Sep 27, 2025Sep 27, 2025

    • HunyuanImage-2.1

      Public
      HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​
      Python
      •
      Other
      •53•1•0•0•Updated Sep 10, 2025Sep 10, 2025

    • Qwen-Image-Lightning

      Public
      Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
      Python
      •
      Apache License 2.0
      •43•0•0•0•Updated Sep 9, 2025Sep 9, 2025

    • deepcompressor

      Public
      Model Compression Toolbox for Large Language Models and Diffusion Models
      Python
      •
      Apache License 2.0
      •86•0•0•0•Updated Aug 14, 2025Aug 14, 2025

    • SpargeAttn

      Public
      SpargeAttention: A training-free sparse attention that can accelerate any model inference.
      Cuda
      •
      Apache License 2.0
      •82•6•0•0•Updated Aug 7, 2025Aug 7, 2025