Repositories list

• LightLLM

  Public

  ModelTC/LightLLM’s past year of commit activity
  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed perf…

  nlpdeep-learningllama+ 4

  nlpdeep-learningllamagptmodel-servingllmopenai-triton

  Python

  •

  Apache License 2.0

  •320320 forks•4k4k stars•8585 issues•4848 pull requests•Updated Apr 19, 2026Apr 19, 2026

• LightX2V

  Public

  ModelTC/LightX2V’s past year of commit activity
  Light Image Video Generation Inference Framework

  video-generationdiffusion-modelswan-video+ 1

  video-generationdiffusion-modelswan-videoauto-regressive-diffusion-model

  Python

  •

  Apache License 2.0

  •187187 forks•2.2k2.2k stars•146146 issues•33 pull requests•Updated Apr 18, 2026Apr 18, 2026

• LightX2V-BLOG

  Public

  ModelTC/LightX2V-BLOG’s past year of commit activity
  CSS

  •00 forks•00 stars•00 issues•00 pull requests•Updated Apr 14, 2026Apr 14, 2026

• LightTTS

  Public

  ModelTC/LightTTS’s past year of commit activity
  LightTTS is a lightweight TTS inference framework optimized for CosyVoice2 and CosyVoice3, enabling fast and scalable speech synthesis in Python and supports st…

  text-to-speechreal-timetts+ 8

  text-to-speechreal-timettsspeech-synthesislow-latencytensorrtinference-optimizationaudio-generationcosyvoicecosyvoice2+ 1

  Python

  •

  Apache License 2.0

  •77 forks•3838 stars•22 issues•00 pull requests•Updated Apr 14, 2026Apr 14, 2026

• general-sam-py

  Public

  ModelTC/general-sam-py’s past year of commit activity
  Python bindings for general-sam and some utilities

  Python

  •

  Apache License 2.0

  •00 forks•55 stars•00 issues•00 pull requests•Updated Apr 14, 2026Apr 14, 2026

• general-sam

  Public

  ModelTC/general-sam’s past year of commit activity
  A general suffix automaton implementation in Rust with Python bindings

  Rust

  •

  Apache License 2.0

  •00 forks•1010 stars•00 issues•11 pull request•Updated Apr 13, 2026Apr 13, 2026

• mtc-token-healing

  Public

  ModelTC/mtc-token-healing’s past year of commit activity
  Token healing implementation in Rust

  Rust

  •

  Apache License 2.0

  •00 forks•44 stars•00 issues•22 pull requests•Updated Apr 13, 2026Apr 13, 2026

• lightx2v_examples

  Public

  ModelTC/lightx2v_examples’s past year of commit activity
  00 forks•00 stars•00 issues•00 pull requests•Updated Apr 9, 2026Apr 9, 2026

• ComfyUI-Lightx2vWrapper

  Public

  ModelTC/ComfyUI-Lightx2vWrapper’s past year of commit activity
  ComfyUI custom node for lightx2v

  comfyuicomfyui-nodes

  comfyuicomfyui-nodes

  Python

  •

  MIT License

  •77 forks•8181 stars•44 issues•00 pull requests•Updated Apr 8, 2026Apr 8, 2026

• LightCompress

  Public

  ModelTC/LightCompress’s past year of commit activity
  [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

  benchmarkdeploymenttool+ 15

  benchmarkdeploymenttoolevaluationpruningquantizationwanawqlarge-language-modelsllm+ 8

  Python

  •

  Apache License 2.0

  •7878 forks•704704 stars•4242 issues•22 pull requests•Updated Apr 1, 2026Apr 1, 2026

• SageAttention3-sparse

  Public
  [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across la…

  Cuda

  •

  Apache License 2.0

  •399399 forks•33 stars•00 issues•00 pull requests•Updated Mar 27, 2026Mar 27, 2026

• MoDES

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

  moecvprvlm+ 5

  moecvprvlmmultimodalmixture-of-expertskimi-vlqwen3-vlcvpr-2026

  Python

  •

  Apache License 2.0

  •00 forks•2626 stars•00 issues•00 pull requests•Updated Mar 16, 2026Mar 16, 2026

• LightMem

  Public

  ModelTC/LightMem’s past year of commit activity
  Python

  •

  Apache License 2.0

  •00 forks•44 stars•00 issues•11 pull request•Updated Mar 4, 2026Mar 4, 2026

• Qwen-Image-Edit-Causal

  Public

  ModelTC/Qwen-Image-Edit-Causal’s past year of commit activity
  In our implementation of Qwen-Image-Edit, we employ block causal attention to improve inference speed.

  Python

  •

  Apache License 2.0

  •22 forks•4848 stars•00 issues•00 pull requests•Updated Feb 16, 2026Feb 16, 2026

• GenRL

  Public

  ModelTC/GenRL’s past year of commit activity
  Reinforcement Learning Framework for Visual Generation

  reinforcement-learninginfrarl+ 7

  reinforcement-learninginfrarlwandpoimagegenerationvideogenerationgrpowan-videowan21

  Python

  •

  Apache License 2.0

  •44 forks•105105 stars•00 issues•00 pull requests•Updated Feb 13, 2026Feb 13, 2026

• QVGen

  Public

  ModelTC/QVGen’s past year of commit activity
  [ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".

  waniclrqat+ 10

  waniclrqatvideo-generationdiffusion-modelsvideogenmodel-quantizationquantization-aware-traininggenerative-aitext-to-video-generation+ 3

  Python

  •

  Apache License 2.0

  •00 forks•2929 stars•00 issues•00 pull requests•Updated Feb 11, 2026Feb 11, 2026

• VideoAlign

  Public
  Python

  •

  MIT License

  •11 fork•22 stars•00 issues•00 pull requests•Updated Feb 10, 2026Feb 10, 2026

• HPSv3

  Public
  Python

  •

  MIT License

  •11 fork•11 star•00 issues•00 pull requests•Updated Feb 10, 2026Feb 10, 2026

• SageAttention

  Public

  ModelTC/SageAttention’s past year of commit activity
  Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and v…

  Cuda

  •

  Apache License 2.0

  •399399 forks•44 stars•00 issues•11 pull request•Updated Feb 10, 2026Feb 10, 2026

• LightKernel

  Public
  HTML

  •

  Apache License 2.0

  •00 forks•44 stars•00 issues•00 pull requests•Updated Feb 4, 2026Feb 4, 2026

• Prototype

  Public
  Python

  •

  Apache License 2.0

  •33 forks•1414 stars•00 issues•00 pull requests•Updated Feb 3, 2026Feb 3, 2026

• modeltc.github.io

  Public
  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Jan 14, 2026Jan 14, 2026

• SpargeAttn

  Public

  ModelTC/SpargeAttn’s past year of commit activity
  [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

  Cuda

  •

  Apache License 2.0

  •9191 forks•00 stars•00 issues•00 pull requests•Updated Jan 12, 2026Jan 12, 2026

• Qwen-Image-Lightning

  Public

  ModelTC/Qwen-Image-Lightning’s past year of commit activity
  Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

  Python

  •

  Apache License 2.0

  •4444 forks•1.3k1.3k stars•3030 issues•00 pull requests•Updated Jan 1, 2026Jan 1, 2026

• verl

  Public

  ModelTC/verl’s past year of commit activity
  verl: Volcano Engine Reinforcement Learning for LLMs

  Python

  •

  Apache License 2.0

  •3.7k3.7k forks•11 star•00 issues•00 pull requests•Updated Dec 15, 2025Dec 15, 2025

• slime

  Public
  slime is an LLM post-training framework for RL Scaling.

  Python

  •

  Apache License 2.0

  •733733 forks•00 stars•00 issues•00 pull requests•Updated Dec 8, 2025Dec 8, 2025

• lightllm-blog

  Public
  SCSS

  •

  MIT License

  •11 fork•11 star•00 issues•11 pull request•Updated Nov 26, 2025Nov 26, 2025

• greedy-tokenizer

  Public

  ModelTC/greedy-tokenizer’s past year of commit activity
  Greedily tokenize strings with the longest tokens iteratively.

  Python

  •

  Apache License 2.0

  •00 forks•00 stars•00 issues•33 pull requests•Updated Nov 24, 2025Nov 24, 2025

• Wan2.2-Lightning

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

  Python

  •

  Apache License 2.0

  •1.9k1.9k forks•283283 stars•2222 issues•00 pull requests•Updated Nov 7, 2025Nov 7, 2025

• LTX-Video-Q8-Kernels

  Public
  Python

  •1818 forks•00 stars•00 issues•00 pull requests•Updated Nov 6, 2025Nov 6, 2025