Who published DeepSeek-V3, and where?

DeepSeek-AI — 2024 (arXiv:2412.19437).

Where can I find a visual explainer of DeepSeek-V3?

Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.

DeepSeek-V3

A 671B mixture-of-experts that activates only 37B — via latent-KV attention and loss-free routing.

DeepSeek-AI · 2024 · Model Architectures. Read the paper ↗

A free, interactive, animated visual explainer of DeepSeek-V3 — every exhibit computed from the real formulas, with verbatim quotes from the source.

Questions

What is DeepSeek-V3?: A 671B mixture-of-experts that activates only 37B — via latent-KV attention and loss-free routing.
Who published DeepSeek-V3, and where?: DeepSeek-AI — 2024 (arXiv:2412.19437).
Where can I find a visual explainer of DeepSeek-V3?: Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.

Related explainers

Qwen3
OLMo 2
MiniMax-01
Gemma 4
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Scalable Diffusion Models with Transformers
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints