Pinned Loading

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

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

   Python 92.2k 22.4k

2. pacer pacer Public

   ONNX model server in C# with adaptive batching, deadline-aware load shedding, and a zero-copy inference path.

   C#

3. matchbook matchbook Public

   C++20 limit order book and matching engine. O(1) cancel, 28M submits/sec at 22ns p50, differentially tested against a naive reference implementation.

   C++

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

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

   Python 36.2k 9k

5. DefectDojo/django-DefectDojo DefectDojo/django-DefectDojo Public

   Open-Source Unified Vulnerability Management, DevSecOps & ASPM

   Python 4.9k 1.9k

6. flock flock Public

   Raspberry Pi face-recognition door lock with presentation-attack detection. 98.2% TAR at 99.8% TRR on LFW.

   Python