This work presents SpecBox, a runtime built around speculative sandbox preallocation tailored for dynamic LLM agent execution pipelines, and implements keyword matching and streaming semantic embedding to enable intent-driven sandbox prewarming, which identifies pending tool execution demands mid-LLM token generation a...
Yi-Hui Zhang, Tian-Yu Wo, Jing-Hao Wang et al.· arXiv.org· 1 citation
Weaver is a low-overhead cross-layer diagnosis framework for GPU kernels that builds a semantic execution graph from operator, kernel timeline, and warp/block evidence, distinguishes blocked and slowed kernels, and reports an interpretable root-cause chain.
This paper presents a tutorial-style, collective-centric taxonomy for collective communication, which organizes recent advances into three layers: communication planning, which generates topology-aware collective schedules; communication execution and adaptation, which maps these schedules onto GPU runtimes and hardwar...
Xue-Bin Song, Menghao Zhang, Yue Liu et al.· IEEE Network· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
