CatherineSue

vllm

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

bookstore

garage

A framework for reproducible reinforcement learning research

maml_rl

Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

occupation-planning-system

This is a project to make a commend to people seeking for jobs, which contributed by my National University Student Innovation Program team

poemmaker

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

vapor