BERT, GPT-2, and OPT Inference Workload
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Inference Throughput | BERT, GPT-2, and OPT Inference Workload BS=2, SL=256 | Original Throughput (tokens/s)57,117.4 | 6 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Inference Throughput | BERT, GPT-2, and OPT Inference Workload BS=2, SL=256 | Original Throughput (tokens/s)57,117.4 | 6 |