Pinned Loading

1. DeepEP DeepEP Public

   Forked from deepseek-ai/DeepEP

   DeepEP: an efficient expert-parallel communication library

   Cuda

2. DeepGEMM DeepGEMM Public

   Forked from deepseek-ai/DeepGEMM

   DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

   Cuda

3. sglang sglang Public

   Forked from sgl-project/sglang

   SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

   Python

4. cutlass cutlass Public

   Forked from NVIDIA/cutlass

   CUDA Templates for Linear Algebra Subroutines

   C++

5. nanochat nanochat Public

   Forked from karpathy/nanochat

   The best ChatGPT that $100 can buy.

   Python

6. SageAttention SageAttention Public

   Forked from thu-ml/SageAttention

   Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

   Cuda