Long-horizon agents have turned LLM serving into an input-heavy workload. Repeated prefills and million-token contexts leave KV caches that strain HBM, SSD capacity, and bandwidth. DeepSeek AI built its newest release around that exact bottleneck. DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters, 196B additional Engram parameters, and a 1M-token context window. It activates 8B parameters per token during prefill and 16B during decode. The main number is a global KV cache footprint of 890 bytes per token, about 1/4 of DeepSeek-V4-Flash and roughly 437x smaller than DeepSeek-V1. Is it deployable? Yes. Open weights ship under an MIT license with vLLM, SGLang, and Transformers paths on Hugging Face, and the research team describes a public API with low, high, and max reasoning tiers. Causal Encoder-Decoder: Half the Prefill The 40-layer backbone is split into a 20-layer causal encoder and a 20-layer decoder. Inspired by YOCO , the decoder does not compute its own global KV. Instead, per-layer projection weights derive it from the final encoder hidden state. Prompt tokens therefore stop at the encoder, which nearly halves prefill compute. Sliding-window attention (SWA) with a 128-token window still runs in every layer, so decoder SWA states are rebuilt by replaying only the last 128 prompt tokens. The research team calls this Decoder SWA Bounded Replay. Compressed Sparse Attention 2 (CSA2) DeepSeek-V4 mixed CSA with Heavily Compressed Attention. V4.1-Flash uses pure CSA2 and attacks cache size along the layer axis. Each CSA2 layer is sta
Source: MarkTechPost