Coding agents powered by large language models (LLMs) repeatedly alternate between model inference and tool calls, creating long-lived sessions with reusable key-value (KV) states and asynchronous request resumptions. Logical readiness, however, does not ensure efficient admission in a shared serving system. Through di...
You-He Jiang, Fang-Cheng Fu, Bin-Hang Yuan et al.· 0 citations
This work presents Crossflow, which makes this boundary elastic without changing node roles, and improves token throughput by 16.2-17.4% on geometric mean over static P/D, and by up to 43.4% at high load, while reducing mean TTFT at every evaluated point.
Yi Xu, Ehsan K. Ardestani, Wen-Yin Fu et al.· 0 citations
This work presents EMA, a memory sharing system that allows GPUs within a server to borrow and reclaim memory from each other, forming an elastic pool of capacity, and ensures performance transparency for both borrowers and lenders.
Occamy-1.0, a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint, is presented and placed at the low-cost knee of the observed cost--performance Pareto frontier.
Wen-Hui Chen, Shi-Wen Cheng, Hao Dong et al.· 3 citations
QK-Restore consistently restores long-context capability at zero training cost while preserving reasoning performance; for instance, on HypeNet-5B it improves S3@256K from $65.4\%$ to $76.4\%$ while maintaining strong reasoning performance.
Xinyu Zhou, Boyuan Zhu, Yi Xu 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.
