LLMs-from-scratch vs ray
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| LLMs-from-scratch | ray | |
|---|---|---|
| Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch | Unified framework for scaling AI and Python applications |
| Stars | 99k | 43k |
| Forks | 15k | 7.8k |
| Open issues | 4 | 3.5k |
| Language | Jupyter Notebook | Python |
| License | Other | Apache-2.0 |
| Last pushed | Jun 2, 2026 | Jul 7, 2026 |
| Categories | Model Training, LLM Frameworks | Developer Tools, Inference & Serving, Data & Retrieval, Model Training, LLM Frameworks |
LLMs-from-scratch
Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.
Jupyter Notebook
ray
Ray is a compute engine that includes a distributed runtime core and libraries tailored for AI tasks like ML training, hyperparameter tuning, reinforcement learning, and serving. It supports data scalability through Datasets, facilitating efficient distribution of datasets across clusters.
Python