Pinned Loading

1. foundry-org/foundry foundry-org/foundry Public

   Foundry materializes CUDA graphs along with its execution context to disk to support fast cold start of serving engines.

   C++ 62 11

2. Terra-Flux/PolyRL Terra-Flux/PolyRL Public

   [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.

   Python 19 1

3. TRAIS-Lab/Dr.Post-Training TRAIS-Lab/Dr.Post-Training Public

   Official implementation of the paper "Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training"

   Jupyter Notebook 4

4. sgl-project/sglang sgl-project/sglang Public

   SGLang is a high-performance serving framework for large language models and multimodal models.

   Python 36.3k 9k

5. Minimap2onGPU/mm2-gb Minimap2onGPU/mm2-gb Public

   Forked from lh3/minimap2

   A versatile pairwise aligner for genomic and spliced nucleotide sequences

   C 24 9

6. xenshinu.github.io xenshinu.github.io Public

   Astro 3 1