arXiv CS
open access
Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
We introduce a mechanism that improves LLM-agent execution: keeping four-byte, GPU-computed control-path routing decisions on-device, avoiding a round-trip to host memory for redispatch. It is faster than host-dispatch in all 36 placements x mechanisms settings in our benchmark across four named GPU
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs#168288
- Queue-Theoretic Admission Control for Multi-Tenant GPU Clusters#414075
- HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous Accelerators#321800
- PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning#1129755
- AutoUVM: Automated Prefetching Framework for LLMs under UVM Oversubscription#973773
Record · ID 1043172
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive