Pinned Repositories
CrowdPlay
A web based platform for collecting human actions in reinforcement learning environments
aArtisanAutotune
A PID Autotuning sketch for aArtisan.
flashinfer
FlashInfer: Kernel Library for LLM Serving
Multi-Agent-ALE
The Arcade Learning Environment (ALE) -- a platform for AI research.
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
oracles_and_followers
Code for the ICML 2023 paper "Oracles & Followers"
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
super
suPER is a collaborative multi-agent RL algorithm
tacheles
a lightweight, open-source blueprint for building powerful and scalable LLM chat applications
tc4plus-coffee-roaster-shield
The TC4+ is improving and expanding on the TC4 Arduino shield for DIY (and commercial) coffee roasters.
mgerstgrasser's Repositories
mgerstgrasser/tacheles
a lightweight, open-source blueprint for building powerful and scalable LLM chat applications
mgerstgrasser/tc4plus-coffee-roaster-shield
The TC4+ is improving and expanding on the TC4 Arduino shield for DIY (and commercial) coffee roasters.
mgerstgrasser/super
suPER is a collaborative multi-agent RL algorithm
mgerstgrasser/oracles_and_followers
Code for the ICML 2023 paper "Oracles & Followers"
mgerstgrasser/aArtisanAutotune
A PID Autotuning sketch for aArtisan.
mgerstgrasser/flashinfer
FlashInfer: Kernel Library for LLM Serving
mgerstgrasser/Multi-Agent-ALE
The Arcade Learning Environment (ALE) -- a platform for AI research.
mgerstgrasser/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
mgerstgrasser/ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
mgerstgrasser/slurm-dashboard
Slurm Dashboard VSCode extension
mgerstgrasser/TC4-shield
mgerstgrasser/trl
Train transformer language models with reinforcement learning.
mgerstgrasser/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
mgerstgrasser/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
mgerstgrasser/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs