7 papers
Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs
Changhai Man, Joongun Park, Hanjiang Wu +3
Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed worklo…
ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling
William Won, Jinsun Yoo, Tuan Ta +16
Distributed machine learning (ML) is a key paradigm for today's large-scale artificial intelligence applications. As model inference arises as an important use case, faithful model…
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…
Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective
Seokjin Go, Joongun Park, Spandan More +5
The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models…
Scaling Intelligence: Designing Data Centers for Next-Gen Language Models
Jesmin Jahan Tithi, Hanjiang Wu, Avishaii Abuhatzera +1
The explosive growth of Large Language Models (LLMs), such as GPT-4 with 1.8 trillion parameters, demands a fundamental rethinking of data center architecture to ensure scalability…