NetX-lab/Frontier

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

Accurate, large-scale, and extensible simulator for LLM inference Systems

A framework for generating realistic LLM serving workloads

A lightweight, configurable, and real-time simulator designed to mimic the behavior of vLLM without the need for GPUs or running actual heavy models.

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

Disaggregated serving system for Large Language Models (LLMs).

Building the Virtuous Cycle for AI-driven LLM Systems