DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse

Article automatically generated from technical news.

Sparse attention already cut long-context compute. The KV cache sitting in HBM and on SSD is now the bottleneck DeepSeek AI went after, and they cut theirs to 890 bytes per token. They released DeepSeek-V4.1-Flash, a 552B MoE model with 1M-token context that activates only 8B parameters per token during prefill and 16B during decode. The global KV cache footprint is roughly 1/4 of DeepSeek-V4-Flash and about 437x smaller than DeepSeek-V1, and the weights are open under an MIT