الباحثون

Shiyu Wang

المنشورات 2

نسخة أولية وصول مفتوح

PHBA: Prefix-State Hybrid Block Attention

Ruijie Li, Jiaxi Hu, Shiyu Wang وآخرون · 2026

Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and precise token retrieval. Existing designs such as Native Hybrid Attention (NHA) combine compressed long-term states with sliding-window attention, but their exact attenti …

نسخة أولية وصول مفتوح

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

DeepSeek-AI, Anyi Xu, B. Li وآخرون · 2026

The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Togeth …

المؤلفون المشاركون

Ruijie Li Jiaxi Hu Yuxuan Liang DeepSeek-AI Anyi Xu B. Li Bangcai Lin Bing Xue BingCheng Xian Bingzheng Xu Bochao Wu Bowei Zhang