Anirudh171202/WhiteLotus

LLM inference engine built from scratch in C++. No PyTorch, no frameworks.

⭐ 12 ⑂ 0 C++ MIT · 2026-04-05推送

https://anirudhsathiya.com/blog/transformer

cpp from-scratch inference llm machine-learning vllm kv-cache bpe bpe-tokenizer

12

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

2026-04-05

最近推送

原文中文

暂无 README