- likes
- 16
- comments
- 1
Post
128GB of on-chip SRAM at rack scale. Memory closer to compute. Infrastructure built for the age of inference. Great conversation between d-Matrix CEO Sid Sheth and Sam Awrabi on what it takes to power the next wave of AI inference, from Corsair and 3D-stacked memory to agentic workloads and the economics of rapidly growing inference demand. The age of inference requires a new approach to AI infrastructure. Watch the full conversation below.