deepseek

Follow one token to two expert ranks and back, then count logical assignments separately from physical network transfers.

Separate FP8 input quantization from accumulation error. A small representable-value example shows when a shared scale loses small values, while the DeepSeek-V3 report supplies one carefully scoped training recipe.

Draw query-head sharing, count actual stored state and compare payloads with explicit model geometry and binary units.

Separate checkpoint memory, expert assignments and retained MLA state. The active parameter count alone cannot predict per-rank fit or token latency.