Products & ServicesEvent: August 31, 2026
Lightbits Labs optimized the kvcache with Inferra, achieving zero hardware changes and breaking the GPU memory wall with prefetch instead of refetch.
Published
Signal category
Products & Services
Quote
“Optimize #kvcache with Inferra from Lightbits Labs.”
— Pete Kapusta|Lightbits Labs team
Company
Lightbits Labs
Best-of-Breed AI Inference Acceleration and Software-Defined Storage Solutions Engineered for Performance and Efficiency
- Industry
- Software Development
- Location
- San Jose, US
- Company size
- 84 employees
Lightbits software maximizes the performance and utilization of the data infrastructure you already own, from high-performance block storage to GPU-accelerated AI inference. Our solutions are engineered to run LLM inference, real-time analytics, and transactional workloads at scale. Lightbits is backed by enterprise technology leaders Cisco Investments, Dell Technologies Capital, Intel Capital, Lenovo, and Micron.
Founded 2016