Applications provide convenient features for users to complete daily tasks. However, different users may have different or even conflicting requirements for the same application, while the requirements of the same user may change over time. Personalizing applications produced by agent-to-app or UI-to-code approaches ca...
Tong Zhang, Yuxuan Cheng, Rui-Min Zhang et al.· 0 citations
The conventional threading model multiplexes software threads onto hardware cores. This model inherently suffers from the overhead of 1) context switching, 2) scheduling, and 3) system event notifications (e.g., I/O interrupts). As computing enters μs-scale, such overheads become the key bottleneck of a wide range of d...
Yi-Ming Yao, Xiao-He Qin, Yi Fan et al.· Proceedings of the ACM SIGOP...· 0 citations
RedKnot establishes a new foundation for AI infrastructure by transforming the KV cache from a monolithic, passive runtime artifact into a dynamic, model-aware runtime substrate for scalable LLM serving.
Yang Liu, Zhao-Kai Luo, Hua-Yi Jin et al.· arXiv.org· 7 citations· ⚡1
Tessera is presented, the first kernel disaggregation system to improve performance and cost efficiency on heterogeneous GPUs for large model inference, and shows that a heterogeneous GPU pair under Tessera can even exceed the throughput of two homogeneous high-end GPUs at a lower cost.
Tian-Cheng Hu, Jin Qin, Zheng Wang et al.· arXiv.org· 0 citations
Evaluating twelve open and proprietary models, it is found that abstraction failure is lawful, and the central finding is a gap between recognition and cross-voice mapping: models identify a structure within one voice far better than they carry it across voices; every model pays this tax, and mapping strong enough to n...
Tong Zhang, Zhiyuan Shi, Yun Peng et al.· 0 citations
This work presents a DeepSeek-V4 realization of RedKnot's head-aware reuse principle, a DeepSeek-V4 realization of RedKnot's head-aware reuse principle, and describes the factorization, position repair, token-row closure, sparse-MoE support, TP8 integration, and the measurement boundaries needed to interpret these resu...
Yang Liu, Zhao-Kai Luo, Hua-Yi Jin et al.· 0 citations
StrataCL introduces registration-on-allocation to realize user-buffer direct communication, and designs communication operators with workload-balanced NPU-core partitioning and NPU-driven SDMA offloading to exploit supernode architecture features.
Tian-Cheng Hu, Jin Qin, Yu-Zheng Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
