| { | |
| "model_family": "whisper", | |
| "variant": "small", | |
| "hardware_target": "amd_npu", | |
| "precision": "int8", | |
| "quantization": { | |
| "method": "INT8", | |
| "calibration_dataset": "librispeech_100h", | |
| "calibration_samples": 10000, | |
| "symmetric": true, | |
| "per_channel": true | |
| }, | |
| "performance": { | |
| "speedup": "75x", | |
| "rtf": 0.003, | |
| "accuracy": "92%", | |
| "tokens_per_sec": 6500, | |
| "power": "6W" | |
| }, | |
| "unicorn_engine": { | |
| "version": "1.0.0", | |
| "backend": "amd_npu", | |
| "kernel": "mlir_aie2", | |
| "optimization_level": 3 | |
| }, | |
| "hardware_requirements": { | |
| "npu": "AMD XDNA 16 TOPS", | |
| "min_driver": "1.0.0", | |
| "supported_cpus": [ | |
| "7040", | |
| "7045", | |
| "8040", | |
| "8045" | |
| ] | |
| } | |
| } |