Can I read Vidur: A Large-Scale Simulation Framework For LLM Inference on EtoBox?

Vidur: A Large-Scale Simulation Framework For LLM Inference by Agrawal, Amey; Kedia, Nitin; Mohan, Jayashree; Panwar, Ashish; Kwatra, Nipun; Gulavani, Bhargav; Ramjee, Ramachandran; Tumanov, Alexey is a scholarly article available to read on EtoBox.

What is Vidur: A Large-Scale Simulation Framework For LLM Inference about?

Optimizing the deployment of Large language models (LLMs) is expensive today since it requires experimentally running an application workload against an LLM implementation while exploring large configuration space formed by system knobs such as parallelization strategies, batching techniques, and scheduling policies. To address this challenge, we present Vidur - a large-scale, high-fidelity, easily-extensible simulation framework for LLM inference performance. Vidur models the performance of LLM operators using a combination of experimental profiling and predictive modeling, and evaluates the end-to-end inference performance for different workloads by estimating several metrics of interest such as latency and throughput. We validate the fidelity of Vidur on several LLMs and show that it estimates inference latency with less than 9% error across the range. Further, we present Vidur-Search, a configuration search tool that helps optimize LLM deployment. Vidur-Search uses Vidur to automatically identify the most cost-effective deployment configuration that meets application performance constraints. For example, Vidur-Search finds the best deployment configuration for LLaMA2-70B in one

Author

Agrawal, Amey; Kedia, Nitin; Mohan, Jayashree; Panwar, Ashish; Kwatra, Nipun; Gulavani, Bhargav; Ramjee, Ramachandran; Tumanov, Alexey

Published

2024

Language

EN