VILA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual-Language Model Inference | VILA Jetson Orin | Throughput (tokens/sec)35.6 | 4 | |
| Visual-Language Model Inference | VILA A100 | Throughput (tokens/sec)155.3 | 4 | |
| Visual-Language Model Inference | VILA RTX 4090 | Throughput (tokens/sec)168.1 | 3 |
Showing 3 of 3 rows