|  | 
| 3 | 3 | Benchmarks Metadata: | 
| 4 | 4 |     Run id:93e36b31-b454-471d-ba62-6b2671585485 | 
| 5 | 5 |     Duration:30.2 seconds | 
| 6 |  | -    Profile:type=sweep, strategies=['synchronous', 'throughput', 'constant', 'constant', 'constant', 'constant',         | 
| 7 |  | -    'constant', 'constant', 'constant', 'constant'], max_concurrency=None                                                | 
| 8 |  | -    Args:max_number=None, max_duration=30.0, warmup_number=None, warmup_duration=None, cooldown_number=None,             | 
| 9 |  | -    cooldown_duration=None                                                                                               | 
| 10 |  | -    Worker:type_='generative_requests_worker' backend_type='openai_http' backend_target='example_target'                 | 
| 11 |  | -    backend_model='example_model' backend_info={'max_output_tokens': 16384, 'timeout': 300, 'http2': True,               | 
| 12 |  | -    'authorization': False, 'organization': None, 'project': None, 'text_completions_path': '/v1/completions',           | 
| 13 |  | -    'chat_completions_path': '/v1/chat/completions'}                                                                     | 
| 14 |  | -    Request Loader:type_='generative_request_loader' data='prompt_tokens=256,output_tokens=128' data_args=None           | 
| 15 |  | -    processor='example_processor' processor_args=None                                                                    | 
|  | 6 | +    Profile:type=sweep, strategies=['synchronous', 'throughput', 'constant', 'constant', 'constant', 'constant', 'constant', 'constant', 'constant', 'constant'],                    | 
|  | 7 | +    max_concurrency=None                                                                                                                                                             | 
|  | 8 | +    Args:max_number=None, max_duration=30.0, warmup_number=None, warmup_duration=None, cooldown_number=None, cooldown_duration=None | 
|  | 9 | +    Worker:type_='generative_requests_worker' backend_type='openai_http' backend_target='example_target' backend_model='example_model' backend_info={'max_output_tokens': 16384,     | 
|  | 10 | +    'timeout': 300, 'http2': True, 'authorization': False, 'organization': None, 'project': None, 'text_completions_path': '/v1/completions', 'chat_completions_path':               | 
|  | 11 | +    '/v1/chat/completions'}                                                                                                                                                          | 
|  | 12 | +    Request Loader:type_='generative_request_loader' data='prompt_tokens=256,output_tokens=128' data_args=None processor='example_processor' processor_args=None | 
| 16 | 13 |     Extras:None | 
| 17 | 14 | 
 | 
| 18 | 15 | 
 | 
| 19 | 16 | Benchmarks Info: | 
| 20 |  | -======================================================================================================================== | 
| 21 |  | -===========================                                                                                              | 
| 22 |  | -Metadata                                    |||| Requests Made  ||| Prompt Tok/Req ||| Output Tok/Req  ||| Prompt Tok    | 
| 23 |  | -Total||| Output Tok Total  ||                                                                                            | 
| 24 |  | -  Benchmark| Start Time| End Time| Duration (s)|  Comp|  Inc|  Err|  Comp|   Inc| Err|   Comp|  Inc|  Err|   Comp|  Inc| | 
| 25 |  | -Err|   Comp|   Inc|   Err                                                                                                | 
| 26 |  | ------------|-----------|---------|-------------|------|-----|-----|------|------|----|-------|-----|-----|-------|-----| | 
| 27 |  | ------|-------|------|------                                                                                              | 
| 28 |  | -synchronous|   16:59:28| 16:59:58|         30.0|    46|    1|    0| 257.1| 256.0| 0.0|  128.0|  0.0|  0.0|  11827|  256| | 
| 29 |  | -0|   5888|     0|     0                                                                                                  | 
| 30 |  | -======================================================================================================================== | 
| 31 |  | -===========================                                                                                              | 
|  | 17 | +=================================================================================================================================================== | 
|  | 18 | +Metadata                                    |||| Requests Made  ||| Prompt Tok/Req ||| Output Tok/Req  ||| Prompt Tok Total||| Output Tok Total  || | 
|  | 19 | +  Benchmark| Start Time| End Time| Duration (s)|  Comp|  Inc|  Err|  Comp|   Inc| Err|   Comp|  Inc|  Err|   Comp|  Inc|  Err|   Comp|   Inc|   Err | 
|  | 20 | +-----------|-----------|---------|-------------|------|-----|-----|------|------|----|-------|-----|-----|-------|-----|-----|-------|------|------ | 
|  | 21 | +synchronous|   16:59:28| 16:59:58|         30.0|    46|    1|    0| 257.1| 256.0| 0.0|  128.0|  0.0|  0.0|  11827|  256|    0|   5888|     0|     0 | 
|  | 22 | +=================================================================================================================================================== | 
| 32 | 23 | 
 | 
| 33 | 24 | 
 | 
| 34 | 25 | Benchmarks Stats: | 
| 35 |  | -======================================================================================================================== | 
| 36 |  | -=======================                                                                                                  | 
| 37 |  | -Metadata   | Request Stats         || Out Tok/sec| Tot Tok/sec| Req Latency (sec)  ||| TTFT (ms)       ||| ITL (ms)      | 
| 38 |  | -||| TPOT (ms)      ||                                                                                                    | 
| 39 |  | -  Benchmark| Per Second| Concurrency|        mean|        mean|  mean|  median|   p99| mean| median|  p99| mean| median| | 
| 40 |  | -p99| mean| median| p99                                                                                                   | 
| 41 |  | ------------|-----------|------------|------------|------------|------|--------|------|-----|-------|-----|-----|-------| | 
| 42 |  | -----|-----|-------|----                                                                                                  | 
| 43 |  | -synchronous|       1.55|        1.00|       198.1|       992.7|  0.64|    0.64|  0.69| 16.8|   16.4| 21.3|  4.9|    4.9| | 
| 44 |  | -5.3|  4.9|    4.9| 5.2                                                                                                   | 
| 45 |  | -======================================================================================================================== | 
| 46 |  | -=======================                                                                                                  | 
|  | 26 | +=============================================================================================================================================== | 
|  | 27 | +Metadata   | Request Stats         || Out Tok/sec| Tot Tok/sec| Req Latency (sec)  ||| TTFT (ms)       ||| ITL (ms)       ||| TPOT (ms)      || | 
|  | 28 | +  Benchmark| Per Second| Concurrency|        mean|        mean|  mean|  median|   p99| mean| median|  p99| mean| median| p99| mean| median| p99 | 
|  | 29 | +-----------|-----------|------------|------------|------------|------|--------|------|-----|-------|-----|-----|-------|----|-----|-------|---- | 
|  | 30 | +synchronous|       1.55|        1.00|       198.1|       992.7|  0.64|    0.64|  0.69| 16.8|   16.4| 21.3|  4.9|    4.9| 5.3|  4.9|    4.9| 5.2 | 
|  | 31 | +=============================================================================================================================================== | 
0 commit comments