DeepSeek and Peking University Release DSpark Paper on June 27, Founder Liang Wenfeng Listed as Author

According to Guru Club, on June 27, DeepSeek's team and Peking University released a research paper titled "DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation." The paper introduces a speculative decoding module to optimize inference performance on existing models DeepSeek-V4-Pro and DeepSeek-V4-Flash. Simultaneously, the team open-sourced DeepSpec, a full-stack codebase for training and evaluating speculative decoding draft models under MIT license. DeepSpec currently supports three implementations: DSpark, DFlash, and Eagle3. Notably, DeepSeek founder Liang Wenfeng is listed as a paper author.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
ManeyToFuturevip
· 1h ago
LFG 🔥
Reply0