7 papers
Sutradhara: An Intelligent Orchestrator-Engine Co-design for Tool-based Agentic Inference
Anish Biswas, Kanishk Goel, Srivarshinee S +5
Agentic applications are LLMs that iteratively invoke external tools to accomplish complex tasks. Such tool-based agents are rapidly becoming the dominant paradigm for deploying la…
ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving
Haoran Qiu, Anish Biswas, Zihan Zhao +9
Large multimodal models (LMMs) demonstrate impressive capabilities in understanding images, videos, and audio beyond text. However, efficiently serving LMMs in production environme…
On Evaluating Performance of LLM Inference Serving Systems
Amey Agrawal, Nitin Kedia, Anmol Agarwal +5
The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluatio…
AI Greenferencing: Routing AI Inferencing to Green Modular Data Centers with Heron
Tella Rajashekhar Reddy, Palak, Rohan Gandhi +8
AI power demand is growing unprecedentedly thanks to the high power density of AI compute and the emerging inferencing workload. On the supply side, abundant wind power is waiting…
Niyama : Breaking the Silos of LLM Inference Serving
Kanishk Goel, Jayashree Mohan, Nipun Kwatra +2
The widespread adoption of Large Language Models (LLMs) has enabled diverse applications with very different latency requirements. Existing LLM serving frameworks rely on siloed in…
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K Kamath, Ramya Prabhu, Jayashree Mohan +3
Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that…