6 papers
LMS-AR: LMS Prediction-based Adaptive Regulator for Memory Bandwidth in Multicore Systems
Sudarshan Srinivasan, Deepak Gangadharan, Dip Goswami
Memory bandwidth contention in multi-core systems severely impacts application performance and quality-of-service (QoS) guarantees. Regulating the shared memory bandwidth mitigates…
PCCL: Process Group-Aware Scalable and Generic Collective Algorithm Synthesizer
William Won, Kartik Lakhotia, Madhu Kumar +2
Distributed machine learning has become increasingly important due to the massive scale of large-scale generative models. Both model parameters and data are distributed across many…
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee +9
Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-pre…
MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian +8
Modern LLM serving now spans multi-stage pipelines including RAG retrieval and KV cache reuse, each with distinct compute, memory, and latency demands. Inference engines expose a l…
FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models
Saeed Rashidi, William Won, Sudarshan Srinivasan +2
Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallel…
Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
Abhimanyu Bambhaniya, Ritik Raj, Geonhwa Jeong +6
Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these gigantic models effi…