Andrej Karpathy
@karpathy · 20 oct. 2025
I quite like the new DeepSeek-OCR paper. It's a good OCR model (maybe a bit worse than dots), and yes data collection etc., but anyway it doesn't matter.
The more interesting part for me (esp as a computer vision at heart who is temporarily masquerading as a natural language
vLLM@vllm_project· 20 oct. 2025🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support.
🧠 Compresses visual contexts up to 20× while keeping
Elon Musk
@elonmusk
Long-term, >99% of input and output for AI models will be photons. Nothing else scales.
00:27 · 21 octobre 2025 · 3,5 M vues
306
458
3,2 k