Pinned Loading

1. Zefan-Cai/KVCache-Factory Zefan-Cai/KVCache-Factory Public

   Unified KV Cache Compression Methods for Auto-Regressive Models

   Python 1.3k 169

2. SEED SEED Public

   (COLING2025) SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding

   Python 10 1

3. SCOPE SCOPE Public

   (ACL2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation

   Jupyter Notebook 35 4

4. Awesome-Efficient-Inference-LLM-RL-Agent Awesome-Efficient-Inference-LLM-RL-Agent Public

   🚀 First survey bridging LLM, RL, and Agentic Eras — 100+ papers on efficient inference from static generation to systematic reasoning and action.

   3