Skip to content

@ModelTC ModelTC

All

    Repositories list

    89 repositories

    • 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 perf…
      nlpdeep-learningllama
      nlpdeep-learningllamagptmodel-servingllmopenai-triton
      Python
      •
      Apache License 2.0
      •372•4.3k•101•72•Updated Oct 15, 2026Oct 15, 2026

    • LightX2V

      Public
      Lightweight Image Video Action Generation Inference Framework
      video-generationworld-modelsdiffusion-models
      video-generationworld-modelsdiffusion-modelshunyuan-videowan-videoltx-videoauto-regressive-diffusion-modelqwen-imagelingbot-worlddreamzero
      Python
      •
      Apache License 2.0
      •285•2.9k•168•52•Updated Oct 15, 2026Oct 15, 2026

    • LightVAE

      Public
      LightVAE: Fast video VAE decoders for Wan2.1, Wan2.2, and MiniMax-H3, plus a compressed H3 reference encoder. Pretrained weights and ComfyUI workflows.
      video-generationcomfyuicomfyui-custom-node
      video-generationcomfyuicomfyui-custom-nodewan21wan22video-vaeminimax-h3
      Python
      •0•25•1•0•Updated Oct 14, 2026Oct 14, 2026

    • general-sam-py

      Public
      Python bindings for general-sam and some utilities
      Python
      •
      Apache License 2.0
      •0•5•0•0•Updated Oct 14, 2026Oct 14, 2026

    • LightX2V-Mac-App

      Public
      Swift
      •0•5•0•0•Updated Oct 14, 2026Oct 14, 2026

    • LightX2V-Skills

      Public
      Agent skills for LightX2V — teach Cursor and AI agents to generate images & videos (t2v, i2v, t2i, s2v) via the lightx2v CLI and x2v.light-ai.top OpenAPI.
      text-to-imageimage-to-videotext-to-video
      text-to-imageimage-to-videotext-to-videodigital-humanai-video-generationagent-skillslightx2v
      MIT License
      •0•1•0•0•Updated Oct 12, 2026Oct 12, 2026

    • LightX2V-BLOG

      Public
      CSS
      •6•5•0•0•Updated Oct 9, 2026Oct 9, 2026

    • mtc-token-healing

      Public
      Token healing implementation in Rust
      Rust
      •
      Apache License 2.0
      •0•4•0•0•Updated Oct 5, 2026Oct 5, 2026

    • Gradio-Lightx2v

      Public
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Sep 18, 2026Sep 18, 2026

    • ComfyUI-Lightx2vWrapper

      Public
      ComfyUI custom node for lightx2v
      comfyuicomfyui-nodes
      comfyuicomfyui-nodes
      Python
      •
      MIT License
      •7•95•4•0•Updated Sep 4, 2026Sep 4, 2026

    • LightX2V-Qwen-Image-Lightning

      Public
      Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
      Python
      •
      Apache License 2.0
      •49•1.4k•32•0•Updated Aug 31, 2026Aug 31, 2026

    • SageAttention

      Public
      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
      •528•3•0•0•Updated Aug 31, 2026Aug 31, 2026

    • mate

      Public
      MUSA AI Tensor Engine
      Python
      •
      Apache License 2.0
      •4•0•0•0•Updated Aug 31, 2026Aug 31, 2026

    • Minimax-H3-Turbo

      Public
      Distill Minimax-H3 into 4 steps
      Python
      •
      Apache License 2.0
      •15•388•4•0•Updated Aug 27, 2026Aug 27, 2026

    • Lightx2v-Platform-Run-Examples

      Public
      Scripts for lightx2v platform run.
      Python
      •0•0•0•0•Updated Aug 16, 2026Aug 16, 2026

    • lightx2v-studio-cli

      Public
      ai, video-generation, image-generation, cli, cursor, agent-skills, lightx2v, openapi
      cliaiopenapi
      cliaiopenapiimage-generationcursorvideo-generationagent-skillslightx2v
      Python
      •
      MIT License
      •0•0•0•0•Updated Aug 14, 2026Aug 14, 2026

    • LightX2V_train_data_examples

      Public
      0•1•0•0•Updated Aug 11, 2026Aug 11, 2026

    • verl

      Public
      verl: Volcano Engine Reinforcement Learning for LLMs
      Python
      •
      Apache License 2.0
      •4.8k•1•0•0•Updated Jul 28, 2026Jul 28, 2026

    • mtc-inc-bpe

      Public
      Incremental BPE tokenization for all prefixes
      Rust
      •
      Apache License 2.0
      •0•7•0•0•Updated Jul 21, 2026Jul 21, 2026

    • general-sam

      Public
      A general suffix automaton implementation in Rust with Python bindings
      Rust
      •
      Apache License 2.0
      •0•10•0•0•Updated Jul 21, 2026Jul 21, 2026

    • RoboLab

      Public
      Python
      •
      Apache License 2.0
      •91•0•0•0•Updated Jul 20, 2026Jul 20, 2026

    • Hunyuan3D-2.1-platform

      Public
      From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
      Python
      •
      Other
      •625•0•0•0•Updated Jul 18, 2026Jul 18, 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
      •528•2•0•0•Updated Jul 7, 2026Jul 7, 2026

    • IsaacLab

      Public
      Unified framework for robot learning built on NVIDIA Isaac Sim
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •4k•0•0•0•Updated Jul 6, 2026Jul 6, 2026

    • lightx2v-plugin-FL

      Public
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Jul 2, 2026Jul 2, 2026

    • lightx2v_examples

      Public
      0•1•0•0•Updated Jun 25, 2026Jun 25, 2026

    • SpargeAttn

      Public
      [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
      Cuda
      •
      Apache License 2.0
      •110•0•0•0•Updated Jun 10, 2026Jun 10, 2026

    • SpargeAttn-Fix

      Public
      [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
      Cuda
      •
      Apache License 2.0
      •110•0•0•0•Updated Jun 10, 2026Jun 10, 2026

    • LightMem

      Public
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Jun 8, 2026Jun 8, 2026

    • q8_kernels

      Public
      Cuda
      •11•0•0•0•Updated May 22, 2026May 22, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.