Pinned Loading

1. ffpa-attn ffpa-attn Public

   Forked from xlite-dev/ffpa-attn

   🤖FFPA: Extend FlashAttention-2 w/ Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA.

   Python

2. Automodel Automodel Public

   Forked from NVIDIA-NeMo/Automodel

   🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

   Python

3. CuTe-MoE-Train CuTe-MoE-Train Public

   Cuda 11

4. cutlass cutlass Public

   Forked from NVIDIA/cutlass

   CUDA Templates for Linear Algebra Subroutines

   C++