@dMatrix(@dMatrix_AI):800+ tokens/sec per user. Heterogeneous inference in action. At #OCP2026, d-Matrix demonstrated live attention/FFN disaggregation across NVIDIA H100 GPUs and memory-centric Corsair™ nodes. Watch the demo:

@dMatrix

@dMatrix_AI

Infinite Inference. No Latency.

Joined February 2022

181 Following 1.5K Followers

@dMatrix@dMatrix_AI

2026.10.15 16:05

800+ tokens/sec per user. Heterogeneous inference in action. At #OCP2026#, d-Matrix demonstrated live attention/FFN disaggregation across NVIDIA H100 GPUs and memory-centric Corsair™ nodes. Watch the demo:

Forward to community

Most Popular Users

998K Followers

957.1K Followers

6.3M Followers

346.7K Followers

1.2M Followers

577.9K Followers

The Wall Street Journal

22.3M Followers

1.1M Followers

504.5K Followers

2.8M Followers

672.9K Followers

2.7M Followers

241.4M Followers

3.4M Followers

5.5M Followers