ModelTC

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

Lightweight Image Video Action Generation Inference Framework

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

Model Quantization Benchmark

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

United Perception

Distill Minimax-H3 into 4 steps

Offline Quantization Tools for Deploy.

Reinforcement Learning Framework for Visual Generation

[CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".

ComfyUI custom node for lightx2v

Summary of system papers/frameworks/codes/tools on training or serving large model

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

Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

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.