TinyChatEngine: On-Device LLM Inference Library

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

EfficientViT is a new family of vision models for efficient high-resolution vision.

[MLSys 2024] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

[CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer