Post #3945 4.38K Mar 6, 2025, 16:34 UTC توضیح بسیار شفاف و بصری طراحی kv cache و اینکه Deepseek چطور این فرایند رو به شکل بسیار کارامدی بهینه کرد .https://youtu.be/0VLAoVGf_74?feature=shared YouTube How DeepSeek Rewrote the Transformer [MLA] Thanks to KiwiCo for sponsoring today’s video! Go to https://www.kiwico.com/welchlabs and use code WELCHLABS for 50% off your first monthly club crate or for 20% off your first Panda Crate! MLA/DeepSeek Poster at 17:12 (Free shipping for a limited time… 👍 10 🙏 1