Popular repositories Loading

1. power-attention power-attention Public

   Attention Kernels for Symmetric Power Transformers

   130 8

2. retention retention Public

   Language modeling with linear-cost context

   Jupyter Notebook 118 14

3. vidrial vidrial Public

   A framework for clean, testable, and high-performance CUDA kernels.

   Cuda 22 3

4. chess_llm chess_llm Public

   Python 4

5. prime-rl prime-rl Public

   Forked from PrimeIntellect-ai/prime-rl

   Async RL Training at Scale

   Python 3

6. power-attention-cuda power-attention-cuda Public

   C++ 2