Hardware
Lightbits set to release KV cache engine to boost GPU performance
Lightbits Labs Ltd. today announced the general availability of Inferra, a software engine designed to improve the economics and performance of artificial intelligence inference by moving key-value ca
Lightbits Labs Ltd. today announced the general availability of Inferra, a software engine designed to improve the economics and performance of artificial intelligence inference by moving key-value cache data beyond the limited high-bandwidth memory attached to graphics processing units. The company, best known as the inventor of the NVMe over TCP storage protocol, is positioning […] The post Lightbits set to release KV cache engine to boost GPU performance appeared first on SiliconANGLE.
Related
- Nscale buys AI infrastructure optimization startup Anyscale for reported $1.65B
- OpenRouter raises $113M to bring order to enterprise AI inference routing
- Decart raises $300M for its AI optimization software, world models
- Nvidia open sources cuFile API, accelerating GPU read/write capability for high-speed storage
Source: SiliconANGLE | 2026-09-09