GPU multitasking offers a promising approach to improving hardware utilization by co-locating concurrent workloads on the same device. However, achieving high resource utilization with minimized interference requires fine-grained, adaptive scheduling. Existing scheduling solutions are fundamentally constrained by a rig...
Ting-Xu Ren, Ru-Wen Fan, Hao Guo et al.· Proceedings of the ACM SIGOP...· 1 citation
Job failures are frequent in large-scale GPU clusters for LLM workloads, leading to significant resource wastage. The vast majority of these are shallow disruptions (e.g., software errors or updates), where only the worker process crashes while the underlying GPU and OS kernel remain intact. Existing recovery systems,...
Hao-Yi Ma, Shi-Wei Gao, You-Min Chen et al.· Proceedings of the ACM SIGOP...· 0 citations
SPORK (Self-sPeculative fORKing), a training-free controller that dispatches the speculated tool call early, overlapping its execution with the remaining chain-of-thought decode, and is orthogonal to token-level speculative decoding.
Huajun Bai, Weiwei Lv, Huichuan Zheng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
