# GPUWorks open-sources a 40MB inference platform for mixed-chip clusters

> Original title: GPUWorks Open-Sources 40MB Inference Platform Running Ascend, PPU, Hygon and NVIDIA in One Cluster

- Source: Pandaily
- Published: 2026-11-04T06:53:47.000Z
- Bad Influence: https://badinfluence.news/items/i2zy9fuhrbmhbdetkp0f3jayk
- Original: https://pandaily.com/gpuworks-open-source-40mb-ai-inference-platform-ascend-t-head-ppu-hygon-dcu-nvidia-1003-servers

## Summary

GPUWorks, a lightweight enterprise AI inference platform, was open-sourced under the Apache-2.0 license on November 4 and runs NVIDIA, AMD, Huawei Ascend, T-Head PPU and Hygon DCU accelerators in one pool. According to the team's own tests, a single server managed 1,003 GPU servers and restored a sleeping model in about four seconds, versus 16 to 17.5 minutes for a cold start from NFS storage.

## Why it matters

The source gives concrete benchmarks for multi-vendor scheduling and model wake-up, showing how mixed accelerator clusters can be managed and how cold-start time was cut.