Popular repositories Loading

1. Efficient-LLM-Inference-Serving-Systems Efficient-LLM-Inference-Serving-Systems Public

   Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → parallelism → vLLM/SGLang, with GPU labs on open models.

   Python 20 2

2. deepagents deepagents Public

   Forked from langchain-ai/deepagents

   The batteries-included agent harness.

   Python

3. pi pi Public

   Forked from earendil-works/pi

   AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

   TypeScript