OSS Radar
YeonwooSung/llm-architecture-from-scratch
Implementing LLM architectures from scratch in PyTorch. Why it matters: useful plumbing for shipping LLM-powered features.
GitHub description: Implementing LLM architectures from scratch in PyTorch
Stars
525
Last 24h
+7
Last 7 days
+49est.
Forks
1
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Daily, since Oct 13, 2026 · 518 → 525
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/YeonwooSung/llm-architecture-from-scratch)<a href="https://ossradar.net/repo/YeonwooSung/llm-architecture-from-scratch"><img src="https://ossradar.net/badge/YeonwooSung/llm-architecture-from-scratch" alt="Trending on OSS Radar"></a>About llm-architecture-from-scratch
YeonwooSung/llm-architecture-from-scratch is a Python project in the LLM tooling category, created 28 days ago. It has 525 GitHub stars and 1 forks, and gained +49 stars over the last 7 days (early estimate), ranking #39 of 162 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- Python
- Category
- LLM tooling
- Created
- Sep 16, 2026
- Last code push
- today (Oct 13, 2026)
- Latest release
- No releases yet
- gemma3
- llama4
- llm
- moe
- qwen3
Similar rising repos
- vllm-project/vllm+7est.
A high-throughput and memory-efficient inference and serving engine for LLMs. Why it matters: useful plumbing for shipping LLM-powered features.
- hiyouga/LlamaFactory+7est.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). Why it matters: useful plumbing for shipping LLM-powered features.
- sgl-project/sglang+7est.
SGLang is a high-performance serving framework for large language models and multimodal models. Why it matters: useful plumbing for shipping LLM-powered features.
- mw00/project-maya+737est.
Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server… Why it matters: useful plumbing for shipping LLM-powered features.
- ollama/ollama+42est.
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. Why it matters: useful plumbing for shipping LLM-powered features.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. Why it matters: useful plumbing for shipping LLM-powered features.