Ressourcen
Erkunden Sie technische Dokumentation, Blog-Artikel und Werkzeuge.
Neueste Ressourcen
CETC Cloud Builds a Domestic GPU Sharing Foundation for a Portable Knowledge Base with HAMi
CETC Cloud needed to bring its intelligent knowledge base to project sites, running text generation, embedding, rerank, knowledge processing, and R&D debugging on a single set of portable devices with domestic GPUs. With Kubernetes and HAMi, per-device dev environment capacity grew from 2 to 30 concurrent Pods, and a single card freed 56 GB of memory and 80% of compute.
View more →8 Models per GPU, ¥200K Saved Monthly: How Sangfor Squeezes Every GPU with K8s + Volcano + HAMi
The AI platform of a 2,000-engineer team kept buying GPUs while most of them sat idle. After rebuilding its compute platform on Kubernetes + Volcano + HAMi, Sangfor raised GPU utilization more than 3×, packed 8+ models onto a single GPU, and cut external model invocation costs by ¥200K per month.
View more →Dynamia and MetaX Complete llm-d Integration: The First Chinese GPU in CNCF's Distributed Inference Ecosystem
Dynamia has partnered with MetaX to complete full adaptation of MetaX C-series GPUs for the llm-d community, validating single-GPU, multi-GPU, and Prefill/Decode disaggregated inference deployments — the first Chinese GPU ever added to llm-d's officially supported accelerator list.
View more →Every Contribution Moves HAMi Forward | HAMi Incubating Community Night Recap
On the evening of September 6, Dynamia, HAMi, and CNCF co-hosted the HAMi Incubating Community Night in Shanghai to celebrate HAMi entering CNCF Incubating. The event launched the HAMi Ambassador Program and honored Maintainers, Approvers, and Contributors.
View more →Subscribe to Our Technical Newsletter
Receive regular updates on product improvements, technical articles, and industry insights delivered directly to your inbox.