10 papers
Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving
Shrikara Arun, Anjaly Parayil, Srikant Bharadwaj +2
Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering. In practice, this creates a new asymmetry: under bursty, heavy-tail…
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, Ming Ma, Zekun Yao +8
Open-Ended Deep Research (OEDR) pushes LLM agents beyond short-form QA toward long-horizon workflows that iteratively search, connect, and synthesize evidence into structured repor…
Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
Shashwat Jaiswal, Shrikara Arun, Anjaly Parayil +8
Low-Rank Adaptation (LoRA) has become the de facto method for parameter-efficient fine-tuning of large language models (LLMs), enabling rapid adaptation to diverse domains. In prod…
SageServe: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling
Shashwat Jaiswal, Kunal Jain, Yogesh Simmhan +9
Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks…
Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers
Rya Sanovar, Srikant Bharadwaj, Renee St. Amant +2
Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of t…
Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Load Balancing
Kunal Jain, Anjaly Parayil, Ankur Mallick +10
Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling in…