Position-independent caching reuses chunk KV caches across positions and requests. Independent encoding, however, omits cross-chunk interactions and can degrade accuracy. In our study, neither PIC training nor rule-based recomputation, alone or combined, consistently recovers full-prefill accuracy. Oracle-guided recomp...
Yue-Yang Pan, Qian-Chao Zhu, Yu-Liang Liu et al.· 0 citations
Hyper-Connections (HC) architectures are increasingly adopted in frontier language models, yet their components remain insufficiently understood and introduce non-negligible training overhead. In this work, we systematically study the HC architecture to understand its components and identify simpler, more efficient des...
Xiang-Dong Zhang, Xiao-Han Qin, Su-Nan Zou et al.· 0 citations
Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired by the success of multi-head attention along the sequence axis, we introduce Multi-Stream Attention Residuals (MSAR), an extension of AttnRes that g...
Xiao-Han Qin, Xiang-Dong Zhang, Tuo Dai et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.