d-Matrix Blog - Tag: H100

Accelerating attention-FFN disaggregation with Corsair and Nvidia H100: inside the industry’s first ultra-low latency heterogeneous pipeline 

Disaggregated AI pipelines have offered an immediate path toward more efficient, extremely low-latency interactive experiences. This includes implementing techniques like prefill/decode disaggregation, speculative decoding, and attention-FFN disaggregation. We’ve already proven… Read More