KKKZOZ's Blog
Recent posts
  1. /72
    2026-01-07

    Think Big, Generate Quick LLM-to-SLM for Fast Autoregressive Decoding

    ICML-24-Workshop
  2. /71
    2026-01-07

    Entropy Adaptive Decoding Dynamic Model Switching for Efficient Inference

    arXiv-2502
  3. /70
    2026-01-07

    Beyond the 80 20 Rule High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

    NeurIPS-25
  4. /69
    2025-12-07

    SLED A Speculative LLM Decoding Framework for Efficient Edge Serving

    SEC-25
  5. /68
    2025-12-06

    KVCache Cache in the Wild Characterizing and Optimizing KVCache Cache at a Large Cloud Provider

    ATC-25KVCache
  6. /67
    2025-12-01

    Token Level Routing Inference System for Edge Devices

    arXiv-2504
  7. /66
    2025-11-16

    SmoothQuant Accurate and Efficient Post-Training Quantization for Large Language Models

    ICML-23Quantization
  8. /65
    2025-11-16

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

    MLSys-25Quantization
  9. /64
    2025-11-15

    LServe Efficient Long-sequence LLM Serving with Unified Sparse Attention

    arXiv-25KVCachesparse-attentionLLM-Inference
  10. /63
    2025-11-13

    Quest Query-Aware Sparsity for Efficient Long-Context LLM Inference

    ICML-24KVCacheLong-Contextsparse-attention