Pinned Loading

1. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 81.9k 17.6k

2. ollama/ollama ollama/ollama Public

   Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

   Go 173k 16.4k

3. deepseek-ai/DeepGEMM deepseek-ai/DeepGEMM Public

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

   Cuda 7.3k 1k

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

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

   Python 28.9k 6.3k

5. llm-scratch-pytorch llm-scratch-pytorch Public

   lm-scratch-pytorch - The code is designed to be beginner-friendly, with a focus on understanding the fundamentals of PyTorch and implementing LLMs from scratch,step by step.

   Jupyter Notebook 100 4

6. OpenSkald OpenSkald Public

   OpenSkald is a self-evolving knowledge-native publishing agent.

   Python 5 2