Overview
Zhenyun Computing Platform is a high-performance compute slicing platform based on Kubernetes and container technology, designed for large-scale machine learning inference and high-performance computing. It supports slicing and fine-grained operation of heterogeneous GPUs. An intuitive interface lets users easily create resource slices matching their computing needs. Combined with inference optimization, it balances high throughput and low latency. It also provides model management similar to the HF large-model repository, with one-click deployment, enabling convenient model management and deployment for rapid development and inference.
Connected profiles
More Model training and deployment products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
“镇云算力平台”是一款基于Kubernetes及容器技术的高性能算力切片平台，专为大规模机器学习模型推理和高性能计算任务打造。 平台支持多种异构显卡的切片和精细化运营。用户可以通过直观、简单的界面，轻松创建匹配匹配自身计算需求的算力资源切片。结合模型推理优化技术，镇云算力平台在高吞吐量和低延迟之间实现了最佳平衡。 此外，平台还提供类似大模型仓库HF的模型管理功能，支持一键部署，使用户能更加便捷地管理和部署模型，快速进行开发和推理工作。