Skip to content
@ModelTC

ModelTC

https://light-ai.top/

Pinned Loading

  1. LightX2V LightX2V Public

    Light Image Video Generation Inference Framework

    Python 2k 162

  2. LightLLM LightLLM Public

    LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

    Python 3.9k 301

  3. LightCompress LightCompress Public

    [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

    Python 680 70

  4. Qwen-Image-Lightning Qwen-Image-Lightning Public

    Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

    Python 1.2k 44

  5. MQBench MQBench Public

    Model Quantization Benchmark

    Python 858 143

  6. Wan2.2-Lightning Wan2.2-Lightning Public

    Forked from Wan-Video/Wan2.2

    Wan2.2-Lightning: Speed up wan2.2 model with distillation

    Python 270 16

Repositories

Showing 10 of 72 repositories
  • MoDES Public

    [CVPR 2026] This is the official PyTorch implementation of "MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping".

    ModelTC/MoDES’s past year of commit activity
    Python 3 Apache-2.0 0 0 0 Updated Feb 21, 2026
  • general-sam-py Public

    Python bindings for general-sam and some utilities

    ModelTC/general-sam-py’s past year of commit activity
    Python 5 Apache-2.0 0 0 0 Updated Feb 20, 2026
  • LightTTS Public

    LightTTS is a lightweight TTS inference framework optimized for CosyVoice2 and CosyVoice3, enabling fast and scalable speech synthesis in Python and supports stream and bistream modes.

    ModelTC/LightTTS’s past year of commit activity
    Python 28 Apache-2.0 7 2 0 Updated Feb 20, 2026
  • LightLLM Public

    LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

    ModelTC/LightLLM’s past year of commit activity
    Python 3,902 Apache-2.0 301 82 35 Updated Feb 20, 2026
  • Qwen-Image-Edit-Causal Public

    In our implementation of Qwen-Image-Edit, we employ block causal attention to improve inference speed.

    ModelTC/Qwen-Image-Edit-Causal’s past year of commit activity
    Python 26 Apache-2.0 2 1 0 Updated Feb 16, 2026
  • mtc-token-healing Public

    Token healing implementation in Rust

    ModelTC/mtc-token-healing’s past year of commit activity
    Rust 4 Apache-2.0 0 0 1 Updated Feb 16, 2026
  • LightMem Public
    ModelTC/LightMem’s past year of commit activity
    Python 4 Apache-2.0 0 0 0 Updated Feb 14, 2026
  • GenRL Public

    Reinforcement Learning Framework for Visual Generation

    ModelTC/GenRL’s past year of commit activity
    Python 40 Apache-2.0 1 0 0 Updated Feb 13, 2026
  • QVGen Public

    [ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".

    ModelTC/QVGen’s past year of commit activity
    Python 13 Apache-2.0 0 0 0 Updated Feb 11, 2026
  • SageAttention3-sparse Public Forked from thu-ml/SageAttention

    [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

    ModelTC/SageAttention3-sparse’s past year of commit activity
    Cuda 1 Apache-2.0 357 0 0 Updated Feb 11, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.