DualPath: Accelerating Agentic LLM Inference by Harvesting Disaggregated KV-Cache Storage I/O
Open Access
- 11 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 16-29
Abstract
No abstract availableThis publication has 14 references indexed in Scilit:
- Phoenix: A Refactored I/O Stack for GPU Direct Storage without Phony Buffers2025
- PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications2025
- TARDIS: A GPU-Centric KV Cache Service for Efficient LLM Inference2025
- Evaluation and Benchmarking of LLM Agents: A Survey2025
- Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures2025
- Fast State Restoration in LLM Serving with HCache2025
- The rise and potential of large language model based agents: a surveyScience China Information Sciences, 2025
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- Efficient Memory Management for Large Language Model Serving with PagedAttention2023
- Resolving Performance Interference in SR-IOV Setups with PCIe Quality-of-Service Extensions2016