Pinned Loading

1. ReasoningPathCompression ReasoningPathCompression Public

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

   Python 33 4

2. dongwonjo/FastKV dongwonjo/FastKV Public

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

   Python 31 5

3. SLEB SLEB Public

   [ICML 2024] Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

   Python 40 6

4. RelayGen RelayGen Public

   Official Implementation of "RelayGen: Intra-Generation Model Switching for Efficient Reasoning"

   Python 3 1