paddler vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| paddler | LLMs-from-scratch | |
|---|---|---|
| Tagline | LLM/VLM load balancer and serving platform built around the ggml ecosystem | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 1.6k | 99k |
| Forks | 89 | 15k |
| Open issues | 25 | 4 |
| Language | Rust | Jupyter Notebook |
| License | Apache-2.0 | Other |
| Last pushed | Jul 7, 2026 | Jun 2, 2026 |
| Categories | Inference & Serving, Model Training | Model Training, LLM Frameworks |
paddler
Paddler is an open-source tool for running, deploying, and scaling Large Language Models (LLMs) on your own infrastructure with features like load balancing, dynamic model swapping, and a web admin panel.
Rust
LLMs-from-scratch
Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.
Jupyter Notebook