
Add to Cart
BERT-Large Inference | CPU only: Xeon Gold 6240 @ 2.60 GHz, precision = FP32, batch size = 128 | V100: NVIDIA TensorRT™ (TRT) 7.2, precision = INT8, batch size = 256 | A100 40GB and 80GB, batch size = 256, precision = INT8.
MLPerf 0.7 RNN-T measured with (1/7) MIG slices. Framework: TensorRT 7.2, dataset = LibriSpeech, precision = FP16.
Order Process
Add Parts to RFQ form | Submit RFQ | We reply within 24 hours |
You confirm order | Payment | Ship out your order |