NeuReality

The Hidden Supply Podcast explores the constraints shaping AI infrastructure: compute, energy, capital, data centers, and the production systems needed to make AI work in production. In our first episode, Why AI Factories Are Bleeding Money, NeuReality CE

For the last two years, enterprise AI adoption was mostly measured in activity: seats provisioned, pilots launched, demos approved, and usage growing. That was enough while AI was treated as experimentation. It is no longer enough when AI becomes infrastr

The inference serving problem is not what most people think it is. It was always assumed that AI training required special, very high-performance, large-scale distributed compute, with HPC infrastructure characteristics, while AI inference was the easy pa

A lot of LLM serving work looks like this: You lower max_model_len and suddenly concurrency improves more than expected.You raise batch size and throughput goes up, but p95 latency gets worse.You move to a faster GPU and decode barely improves.You turn on

When Jensen Huang addressed 30,000 attendees at NVIDIA GTC and declared that the data center of the future is a "token factory," the message was clear: AI infrastructure is being redefined. For years, AI infra was measured by raw compute capacity: GPUs, F

This is the second post in our series. Last time, we looked at the "parallelismsalad" of DP, TP, PP, and EP. Today, I want to address the elephant in the room: Why does serving an LLM feel like systems hell, when "classical" ML felt almost boring? If you'

Israeli AI startup NeuReality names Google Labs product director Shalini Agarwal as strategic adviser to drive enterprise adoption of its NR-NEXUS inference platform.

As AI workloads scale from individual servers to sprawling gigafactories, the network has quietly become one of the most consequential bottlenecks in AI infrastructure. Traditional NICs were never designed for the collective communication patterns of dist

If you've ever tried to serve an LLM and immediately thought "why the hell is this so much harder than training?", welcome to the club. Training is just math. Inference is systems hell: VRAM that fills up in weird ways, interconnect that decides whether y