Pinned Loading

1. ARCQuant ARCQuant Public

   [ACL 2026 Main] Code for the paper "ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs"

   Cuda 31 7

2. SharQ SharQ Public

   Code for the paper “SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference”

   Python 13 2

3. lwy2020/MicroMix lwy2020/MicroMix Public

   MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models

   Cuda 30 5

4. block-scaled-ptq-research block-scaled-ptq-research Public

   A Codex skill for designing, implementing, and evaluating post-training quantization research with block-scaled formats.

   Python