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 performance.

  nlpdeep-learningllama+ 4gptmodel-servingllmopenai-triton

  Python

  •

  Apache License 2.0

  •283•3.8k•81•34•Updated Nov 26, 2025Nov 26, 2025

• LightX2V

  Public

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

  video-generationdiffusion-modelswan-video+ 1auto-regressive-diffusion-model

  Python

  •55•921•57•0•Updated Nov 26, 2025Nov 26, 2025

• lightllm-blog

  Public

  ModelTC/lightllm-blog’s past year of commit activity
  SCSS

  •

  MIT License

  •1•1•0•0•Updated Nov 26, 2025Nov 26, 2025

• LightMem

  Public

  ModelTC/LightMem’s past year of commit activity
  Apache License 2.0

  •0•0•0•1•Updated Nov 26, 2025Nov 26, 2025

• LightKernel

  Public

  ModelTC/LightKernel’s past year of commit activity
  HTML

  •

  Apache License 2.0

  •0•3•0•0•Updated Nov 26, 2025Nov 26, 2025

• ComfyUI-Lightx2vWrapper

  Public

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

  comfyuicomfyui-nodes

  Python

  •

  MIT License

  •7•54•2•0•Updated Nov 25, 2025Nov 25, 2025

• mtc-incremental-bpe

  Public

  ModelTC/mtc-incremental-bpe’s past year of commit activity
  Incremental BPE tokenization for all prefixes

  Rust

  •

  Apache License 2.0

  •0•0•0•0•Updated Nov 25, 2025Nov 25, 2025

• general-sam

  Public
  A general suffix automaton implementation in Rust with Python bindings

  Rust

  •

  Apache License 2.0

  •0•8•0•0•Updated Nov 25, 2025Nov 25, 2025

• mtc-token-healing

  Public

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

  Rust

  •

  Apache License 2.0

  •0•4•0•0•Updated Nov 25, 2025Nov 25, 2025

• 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

  •0•5•0•0•Updated Nov 25, 2025Nov 25, 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

  •0•0•0•3•Updated Nov 24, 2025Nov 24, 2025

• slime

  Public

  ModelTC/slime’s past year of commit activity
  slime is an LLM post-training framework for RL Scaling.

  Python

  •

  Apache License 2.0

  •282•0•0•0•Updated Nov 20, 2025Nov 20, 2025

• modeltc.github.io

  Public
  HTML

  •0•0•0•0•Updated Nov 19, 2025Nov 19, 2025

• LightCompress

  Public

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

  benchmarkdeploymenttool+ 15evaluationpruningquantizationwanawqlarge-language-modelsllm+ 8

  Python

  •

  Apache License 2.0

  •62•627•41•0•Updated Nov 19, 2025Nov 19, 2025

• lightx2v_examples

  Public

  ModelTC/lightx2v_examples’s past year of commit activity
  0•0•0•0•Updated Nov 12, 2025Nov 12, 2025

• Wan2.2-Lightning

  Public

  ModelTC/Wan2.2-Lightning’s past year of commit activity
  Wan2.2-Lightning: Speed up wan2.2 model with distillation

  Python

  •

  Apache License 2.0

  •1.4k•226•17•0•Updated Nov 7, 2025Nov 7, 2025

• LTX-Video-Q8-Kernels

  Public
  Python

  •15•0•0•0•Updated Nov 6, 2025Nov 6, 2025

• SageAttention-1104

  Public

  ModelTC/SageAttention-1104’s past year of commit activity
  [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.

  Cuda

  •

  Apache License 2.0

  •270•0•0•0•Updated Nov 6, 2025Nov 6, 2025

• FlashVSR

  Public

  ModelTC/FlashVSR’s past year of commit activity
  Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.

  Python

  •

  Apache License 2.0

  •80•1•0•0•Updated Nov 5, 2025Nov 5, 2025

• ComfyUI-LightVAE

  Public
  Python

  •

  Apache License 2.0

  •7•33•13•0•Updated Nov 3, 2025Nov 3, 2025

• Qwen-Image-Lightning

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

  Python

  •

  Apache License 2.0

  •39•997•19•0•Updated Oct 14, 2025Oct 14, 2025

• HBP

  Public
  [NeurIPS 2025] This is the official PyTorch implementation of "Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM".

  Python

  •

  Apache License 2.0

  •0•4•0•0•Updated Sep 30, 2025Sep 30, 2025

• TFMQ-DM

  Public

  ModelTC/TFMQ-DM’s past year of commit activity
  [CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".

  highlightquantizationcvpr+ 8ldmdiffusion-modelstpamipost-training-quantizationddimstable-diffusioncvpr2024+ 1

  Jupyter Notebook

  •

  Apache License 2.0

  •4•109•0•0•Updated Sep 29, 2025Sep 29, 2025

• 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 video models.

  Cuda

  •

  Apache License 2.0

  •270•2•0•0•Updated Aug 16, 2025Aug 16, 2025

• fa3

  Public
  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •1•0•0•0•Updated Aug 7, 2025Aug 7, 2025

• flash-attn-3-build

  Public
  Dockerfile

  •2•0•0•0•Updated Jul 24, 2025Jul 24, 2025

• HarmoniCa

  Public
  [ICML 2025] This is the official PyTorch implementation of "🎵 HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration".

  accelerationicmldit+ 6pixartdiffusion-modelsdiffusion-transformerpixart-sigmafeature-cachingicml-2025

  Python

  •

  Apache License 2.0

  •1•44•0•0•Updated Jul 10, 2025Jul 10, 2025

• LightTTS

  Public
  Light-tts is a lightweight TTS inference framework optimized for CosyVoice2, enabling fast and scalable speech synthesis in Python.

  Python

  •

  Apache License 2.0

  •0•11•0•0•Updated Jun 24, 2025Jun 24, 2025

• OmniBal

  Public
  [ICML 2025] This is the official PyTorch implementation of "OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance".

  vlmicml-2025

  Python

  •

  Apache License 2.0

  •3•26•3•0•Updated Jun 16, 2025Jun 16, 2025

• lightx2v_comfyui_node

  Public
  0•0•0•0•Updated Apr 28, 2025Apr 28, 2025