Pinned Loading

1. CHESS CHESS Public

   [EMNLP 2024] CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification

   Python 4 1

2. A2ATS A2ATS Public

   [ACL 2025 Findings] A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization

   Python 5

3. microsoft/BitNet microsoft/BitNet Public

   Official inference framework for 1-bit LLMs

   Python 28.4k 2.3k

4. Eddie-Wang1120/llama.cpp Eddie-Wang1120/llama.cpp Public

   Forked from ggml-org/llama.cpp

   LLM inference in C/C++

   C++ 25 25