P2 Title: An AI Stack: From Scaling AI Workloads to Evaluating LLMs
AI 技术栈：从扩展 AI 工作负载到评估 LLM
ASPLOS Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 22026匹配度 2/10 · 该论文主要介绍 Ray、vLLM、SGLang 和 LMArena 等 AI 系统/推理/评测基础设施，属于 LLM 系统与评测方向，与用户核心关注的静态分析、Agentic 程序分析、浮点/贝叶斯程序分析以及 LLM+形式化验证没有直接交集；仅在“评测/benchmark”层面与用户对 benchmark 的兴趣有极弱关联。引用 0inbox
摘要未给出定量实验；评估体现为这些系统在实际 AI 工作负载扩展、推理吞吐与 LLM 基准测试中的应用，并在此基础上总结关键经验教训与未来方向。
原文摘要（Abstract）
Large language models (LLMs) have taken the world by storm, enabling new applications, intensifying GPU shortages, and raising concerns about the accuracy of their outputs. In this talk, I will present several projects I have worked on to address these challenges. Specifically, I will focus on Ray, a distributed framework for scaling AI workloads, vLLM and SGLang, two high-throughput inference engines for LLMs, and LMArena, a platform for accurate LLM benchmarking. I will conclude with key lessons learned and outline directions for future research
@inproceedings{Stoica26,
title = {Title: An AI Stack: From Scaling AI Workloads to Evaluating LLMs},
author = {Ion Stoica},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3795612}
}