@dMatrix
@dMatrix_AI
Infinite Inference. No Latency.
가입 February 2022
181 팔로잉 중 1.5K 팬
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:
더 보기
