@dMatrix
@dMatrix_AI
Infinite Inference. No Latency.
가입 February 2022
181 팔로잉 중 1.5K 팬
845 tokens/sec per user. ~50% lower latency.
d-Matrix Corsair + NVIDIA H100 are redefining AI inference with attention-FFN disaggregation.
Faster inference. Smarter compute.
Read more:
더 보기
