GPUWorks open-sources Apache-2.0 inference platform for mixed-chip GPU clusters
Overview
FlitAI open-sources GPUWorks, a lightweight enterprise AI inference platform, under the Apache-2.0 license on November 4.
The code is hosted on GitHub under the FlitAI organization, and enterprises and developers may use and modify it or contribute inference templates and chip adaptations.
The platform 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. These figures come from the developers and have not been independently verified.
Written by AI from the articles below · updated Nov 4, 2:37 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- PandailyNewsGPUWorks open-sources a 40MB inference platform for mixed-chip clusters
AIGPUWorks, 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.
Heat Trend
Not enough continuous observations to show a trend yet.