Saved in:
Bibliographic Details
Main Authors: Yang, Mengtian, Zhang, Zhekun, Wu, Mingheng, Yan, Jianwen, Sun, Hanshi, Chang, Li-wen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17164
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Deploying large-scale LLM training and inference with optimal performance is exceptionally challenging due to a complex design space of parallelism strategies, system optimizations, and hardware configurations. Accurate and rapid performance simulation is critical for guiding optimization efforts and system studies by validating "what-if" Hooker Figure hypotheses. To address this, we introduce Charon, a unified, modular, and fine-grained simulator for accurately predicting LLM performance. Experiments show Charon achieves high accuracy across different models and configurations, with an overall prediction error consistently under 5.35%, and even under 3.74% for training with a large-scale GPU cluster. In a practical inference deployment case, Charon discovered a configuration that improved system throughput over an engineering-tuned baseline, demonstrating its significant real-world value.