Unverified50% confidenceFactExact time
The model introduces QSA, a self-developed absorptive Attention mechanism from Tongyi Qianwen, which is highly similar in concept to DeepSeek's DSA (DeepSeek Sparse Attention).
1
Sources
50%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSeek 8B adopts the GQA (Grouped Query Attention) attention mechanism to reduce VRAM usage during inference.78% similarVerifiedDeepSeek V4 adopts a proprietary hierarchical compressed attention strategy, featuring two alternating attention modes: CSA (Compressed Sink Attention) and HCA (Heavy Compressed Attention).77% similarUnverifiedDeepSeek-V3.2-Exp首次引入自研的DeepSeek Sparse Attention（DSA）稀疏注意力技术75% similarVerifiedDeepSeek adopts a Mixture of Experts (MoE) architecture and a Multi-head Latent Attention (MLA) mechanism.73% similarUnverified经验回放最早在DeepMind的DQN算法中被提出，智能体将过去的交互经验存储在缓冲区中，训练时随机采样以提高样本利用效率72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/863815API
curl https://kongchang.com/api/v1/knowledge/claims/863815MCP
get_claim(id=863815)