# Open-source platform simulates LLM serving bottlenecks from chips to clusters

> Original title: From chips to clusters: simulating LLM serving at scale.

- Source: LMSYS Org
- Published: 2026-11-07T23:08:01.000Z
- Bad Influence: https://badinfluence.news/items/xq3c14xkgvcmqv97wuhwlcpym
- Original: https://x.com/lmsysorg/status/2119205259491115255

## Summary

Zhenhua Zhu of Tsinghua Shenzhen International Graduate School presents an open-source platform for finding bottlenecks in LLM serving. It models compute, memory, interconnects and serving software, from chips to clusters.

## Post

From chips to clusters: simulating LLM serving at scale.

Zhenhua Zhu from Tsinghua Shenzhen International Graduate School on an open-source platform for finding bottlenecks across compute, memory, interconnects and serving software.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWjtp9YaoAABCsj.jpg&mode=thumb&exp=1794355200&sig=b00210d0633c7f53)