Tensormesh, an AI infrastructure company focused on inference optimization, secured $20 million in funding from AMD Ventures, CoreWeave, NVentures, Valley Capital Partners and Laude Ventures, bringing total funding to $24.5 million. The company also announced the general availability of Tensormesh Inference, its AI inference platform built around KV caching technology.
Funding to Scale AI Infrastructure
The new capital will support product development, enterprise expansion and deeper integrations with AI hardware and cloud providers. Tensormesh aims to reduce one of enterprise AI’s biggest costs: recomputing repeated inputs during inference.
By reusing previously processed data through KV caching, the platform helps enterprises reduce GPU costs and latency by up to 10x.
"Tensormesh offers a new vision on the significance of the intermediate data that LLMs generate when processing prompts. Behind the term KV cache is a whole concept of AI interpretation of the question it is asked. This makes it a whole new class of data and a category Tensormesh is uniquely positioned to define. We’re excited to keep building," said Junchen Jiang, co-founder and CEO of Tensormesh.
Enterprise AI Efficiency and Open-Source Expansion
Tensormesh Inference is available through serverless and reserved deployment models, with real-time analytics for cache usage and cost savings.
The company will also continue investing in LMCache, its open-source KV caching project integrated with platforms including TensorRT, AWS SageMaker and vLLM.
“KV caching represents one of the most consequential and underexplored opportunities in AI infrastructure today. Tensormesh has built the only platform that makes this technology production-ready for the enterprise, and we believe it will become a critical part of how every serious AI deployment is run," said Steve O'Hara, founder and managing partner at Valley Capital Partners and a Tensormesh board member..