US EditionPublished • loading... • Updated
Zilliz Collaborates with Pliops to Enable Billion-Scale Vector Search at Storage-Level Costs
The integration enables enterprises to run multi-billion embedding vector searches at storage-level costs, improving AI inference efficiency and reducing infrastructure overhead.
- Zilliz and Pliops announced a partnership from Redwood City to integrate Milvus with Pliops' hardware-accelerated storage, enabling multi-billion-scale vector search.
- Enterprises facing larger RAG workloads must handle billions of embeddings, and Zilliz plans enhancements to expand context windows while improving inference efficiency and reducing infrastructure overhead.
- Adding Storage APIs and tiering to Milvus formalizes multi-tier support with a dual-tier architecture using flash tier and S3 tier , enhanced by KV mapping for efficient caching.
- Zilliz Cloud will support deployments across major clouds, and the Milvus RFC for Near Compute Storage is available now on GitHub, enabling enterprises deploying larger models.
- By marrying hardware-accelerated storage with distributed vector search, Pliops' LightningAI introduces affordable GenAI scaling, while Milvus and Zilliz combine storage and retrieval intelligence for enterprise RAG backed by Zilliz investors.
Insights by Ground AI
25 Articles
25 Articles
SC25: Pliops Accelerates GenAI Data Access and Announces Collaboration with Zilliz
At SC25, Pliops is to showcase major advancements in AI infrastructure and announce a new collaboration with Zilliz aimed at enabling affordable, large-scale Retrieval-Augmented Generation (RAG).This initiative targets multi-billion-scale vector databases at storage-level costs by combining Pliops’ LightningAI architecture with Zilliz’s Milvus vector database technology. Enterprises increasingly rely on vector search and large-context retrieval …
Coverage Details
Total News Sources25
Leaning Left2Leaning Right1Center11Last UpdatedBias Distribution79% Center
Bias Distribution
- 79% of the sources are Center
79% Center
14%
C 79%
Factuality
To view factuality data please Upgrade to Premium
