Pinned Loading

1. TidalDecode TidalDecode Public

   TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

   Python 25 1

2. flexflow/flexflow-train flexflow/flexflow-train Public

   Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

   C++ 1.7k 233

3. Blocking_Waived_Estimation Blocking_Waived_Estimation Public

   This repo aims to solve worst case delay of relatively complicated network architecture with [1] Trajectory Approach; [2] Network Calculus; [3] Compositional Performance Analysis (CPA); and [4] Flo…

   Python 2

4. Xcircuit-GPT-Circuit-Classifier Xcircuit-GPT-Circuit-Classifier Public

   Jupyter Notebook 1 2

5. mit-han-lab/TinyChatEngine mit-han-lab/TinyChatEngine Public

   TinyChatEngine: On-Device LLM Inference Library

   C++ 785 74

6. JackFram/ralm-sys JackFram/ralm-sys Public

   Python 5 1