Resources
time-to-first-token
patchy631/time-to-first-token
A ten-week hands-on roadmap for learning LLM inference serving from vLLM to benchmarking.
Topics
Related projects
llm-action25.3kA curated Chinese knowledge base sharing LLM training, fine-tuning, inference, and deployment tutorials with hands-on code.
ml-engineering19.7kAn open book on machine learning engineering, collecting practical guides, scripts, and troubleshooting for training and serving large models.
LLM-Engineers-Handbook5.4kThe companion code for the LLM Engineer's Handbook, teaching end-to-end LLM and RAG systems on AWS.
second-brain-ai-assistant-course3.1kAn open-source course teaching how to build a Second Brain AI assistant with RAG, agents, fine-tuning and LLMOps.
agent-lightning18.9kA lightweight RL framework for training AI agents directly with their real harnesses and environments.
litgpt13.8kA developer framework with from-scratch implementations of 20+ LLMs plus proven recipes to pretrain, finetune, evaluate, and deploy them.