From the 1 of 10 linked papers with an AI index.
10 papers
ACID: Adaptive Caching for vIDeo generation
Om Agrawal, Saurabh Agarwal, Aditya Akella
The paper introduces ACID, a training-free wrapper that dynamically adjusts caching thresholds during video diffusion model inference to accelerate generation while maintaining vis…
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack
Nitin Kedia, Saurabh Agarwal, Myungjin Lee +1
Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation. Their bidirectional attent…
Harmonia: End-to-End RAG Serving Optimization
Saurabh Agarwal, Bodun Hu, Luis Pabon +3
Retrieval-Augmented Generation (RAG) improves the reliability of large language models by integrating external knowledge, but serving RAG pipelines efficiently is challenging becau…
CUCo: An Agentic Framework for Compute and Communication Co-design
Yoga Sri Varshan Varadharajan, Bodun Hu, Saurabh Agarwal +1
Computation and communication in distributed LLM training and inference are traditionally optimized in isolation; expert-crafted systems such as DeepEP, FLUX, and TokenWeave show t…
TrainMover: An Interruption-Resilient Runtime for ML Training
ChonLam Lao, Jiaqi Gao, Jiamin Cao +13
Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solutions like checkpoint-restart or runtime r…
Nalar: An agent serving framework
Marco Laju, Donghyun Son, Saurabh Agarwal +4
LLM-driven agentic applications increasingly automate complex, multi-step tasks, but serving them efficiently remains challenging due to heterogeneous components, dynamic and model…