Library
Visual explainers
Standalone, browser-based guides with diagrams, equations, and interactive controls.
Model architecture
DeepSeek-V4.1-Flash
Follow CED prefill and decode, CSA2 cache sharing, hierarchical sparse indexing, and bounded replay through the 40-layer model.
GPU algorithms
FlashAttention
See how tiling and online softmax reduce HBM traffic without approximating attention.
Attention systems
Sol-Attn
Trace sequence parallelism, communication costs, and the system design behind long-context attention.
Model architecture
MiniMax H3
Explore lightning attention, mixture-of-experts routing, and the model's hybrid recurrent structure.
World models
Looped World Models
Understand iterative latent refinement, adaptive computation, and the evidence behind recurrent depth.
Numerical formats
Blackwell GPU and FP4
Compare low-precision formats and follow FP4 values through Blackwell tensor-core execution.