Pinned Loading

1. Token-Sparse-Attention Token-Sparse-Attention Public

   [ICML 2026] Official Implementation of "Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection"

   Python 10

2. jiwonsong-dev/ReasoningPathCompression jiwonsong-dev/ReasoningPathCompression Public

   [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"

   Python 32 5

3. FastKV FastKV Public

   [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration"

   Python 34 7

4. BinaryMoS BinaryMoS Public

   [NeurIPS 2024] Official Implementation of "Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models"

   Python 11

5. CEChallenge-2023 CEChallenge-2023 Public

   This repository is for 2023 Samsung Computer Engineering Challenge with 3rd place

   Python

6. PIM_Term-Project-2022 PIM_Term-Project-2022 Public

   This repository is for the term project of Topics in Integrated Circuit Design (430.831A 002).

   Python