deepseek-v4.1POST
Flash-1017's fused attention-MLP block cuts latency, a reply argues
A reply argues DeepSeek's fused attention-MLP block lets Flash-1017 cut latency while scaling compute on a larger token corpus, contrasted with another model's retrieval-augmented decoder.
ADL
@ADLXBTArchived 10 days agoOriginally posted 2026.10.22
ADL @ADLXBTOriginally posted 2026.10.22
@YxzRainy the advantage lies in the fused attention‑mlp block that deepseek uses, letting flash‑1017 cut latency while scaling compute on a larger token corpus, claude fable adds a retrieval‑augmented decoder that boosts per‑token reasoning
x.com/adlxbt/status/2113094578874261750Archived 2026.10.22 11:59