Popular repositories Loading

1. plasma plasma Public

   Forked from ray-project/plasma

   A minimal shared memory object store design

   C

2. ThunderKittens ThunderKittens Public

   Forked from HazyResearch/ThunderKittens

   Tile primitives for speedy kernels

   Cuda

3. tiny-llm tiny-llm Public

   Forked from skyzh/tiny-llm

   (🚧 WIP) a course of LLM inference serving on Apple Silicon for systems engineers.

   Python

4. tlb_shootdowns tlb_shootdowns Public

   Forked from bitcharmer/tlb_shootdowns

   C

5. SageAttention SageAttention Public

   Forked from thu-ml/SageAttention

   [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

   Cuda

6. mini-sglang mini-sglang Public

   Forked from sgl-project/mini-sglang

   A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

   Python