Pinned Loading

1. mit-han-lab/omniserve mit-han-lab/omniserve Public

   [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

   C++ 867 73

2. mit-han-lab/llm-awq mit-han-lab/llm-awq Public

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

   Python 3.7k 328

3. mit-han-lab/torchsparse mit-han-lab/torchsparse Public

   [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

   Cuda 1.5k 192

4. mit-han-lab/fastrl mit-han-lab/fastrl Public

   [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

   Python 187 17

5. mit-han-lab/foreact mit-han-lab/foreact Public

   [CVPR 2026 Highlight] ForeAct: Steering Your VLA with Efficient Visual Foresight Planning

   Python 103 7

6. NVlabs/VILA NVlabs/VILA Public

   VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

   Python 3.9k 337