A SuperGLUE entry would worth a thousand blog posts.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| NVIDIA Slashes BERT Training and Inference Times | 0 | 307 | August 21, 2022 | |
| NVIDIA Announces TensorRT 8 Slashing BERT-Large Inference Down to 1 Millisecond | 0 | 484 | July 20, 2021 | |
| Real-Time Natural Language Processing with BERT Using NVIDIA TensorRT (Updated) | 0 | 554 | July 20, 2021 | |
| Replicate 2.2ms inference time on BERT | 0 | 361 | August 22, 2019 | |
| Training and Fine-tuning BERT Using NVIDIA NGC | 0 | 497 | August 25, 2020 | |
| Microsoft Trains Turing-NLG, World’s Largest Transformer Language Model | 0 | 323 | August 21, 2022 | |
| Deploying GPT-J and T5 with FasterTransformer and Triton Inference Server | 7 | 1133 | April 19, 2023 | |
| Accelerated Inference for Large Transformer Models Using FasterTransformer and Triton Inference Server | 1 | 617 | August 10, 2023 | |
| Optimizing and Accelerating AI Inference with the TensorRT Container from NVIDIA NGC | 0 | 384 | August 25, 2020 | |
| NVIDIA Announces TensorRT 6; Breaks 10 millisecond barrier for BERT-Large | 0 | 275 | August 21, 2022 |