| 1 | { |
| 2 | "defaults": { |
| 3 | "qps_list": [ |
| 4 | "inf" |
| 5 | ], |
| 6 | "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200], |
| 7 | "server_environment_variables": { |
| 8 | "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120 |
| 9 | }, |
| 10 | "server_parameters": { |
| 11 | "dtype": "bfloat16", |
| 12 | "model": "openai/whisper-large-v3-turbo" |
| 13 | }, |
| 14 | "client_parameters": { |
| 15 | "model": "openai/whisper-large-v3-turbo", |
| 16 | "backend": "openai-audio", |
| 17 | "endpoint": "/v1/audio/transcriptions", |
| 18 | "dataset_name": "hf", |
| 19 | "dataset_path": "openslr/librispeech_asr", |
| 20 | "hf_subset": "clean", |
| 21 | "hf_split": "test", |
| 22 | "no_stream": "", |
| 23 | "no_oversample": "", |
| 24 | "temperature": 0, |
| 25 | "num_prompts": 200 |
| 26 | } |
| 27 | }, |
| 28 | "tests": [ |
| 29 | { |
| 30 | "test_name": "serving_whisper_large_v3_turbo_librispeech_clean_tp1", |
| 31 | "server_parameters": { |
| 32 | "tensor_parallel_size": 1 |
| 33 | }, |
| 34 | "client_parameters": {} |
| 35 | } |
| 36 | ] |
| 37 | } |