
llm-architecture-from-scratch
by YeonwooSung (personal account)
Implementing LLM architectures from scratch in PyTorch (description from the project’s GitHub page)
Repository facts
- Stars
- 1,009
- Forks
- 4
- Open issues and pull requests
- 0
- Primary language
- Python
- License
- BSD 3-Clause "New" or "Revised" License (BSD-3-Clause)
- Owner
- YeonwooSung · Personal account
- Created
- Sep 16, 2026
- Last push
- Oct 17, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/yeonwoosung--llm-architecture-from-scratch/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/yeonwoosung--llm-architecture-from-scratch/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/yeonwoosung--llm-architecture-from-scratch.svg" alt="Ranked #6,089 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 3,107: AI-Hypercomputer/maxtext
A simple, performant, and scalable Jax LLM!
2,445 starsPythonApache-2.0Last push Oct 18, 2026
Rank 6,010: NVIDIA-NeMo/Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
1,027 starsPythonApache-2.0Last push Oct 18, 2026
Rank 978: zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
8,342 starsPythonApache-2.0Last push Sep 22, 2026
Rank 2,371: johnbean393/Sidekick
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software.…
3,320 starsSwiftMITLast push Sep 30, 2026
Rank 43: vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
94,068 starsPythonApache-2.0Last push Oct 18, 2026
Rank 513: modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3…
15,871 starsPythonApache-2.0Last push Oct 18, 2026