10 lines
1.8 KiB
JSON
10 lines
1.8 KiB
JSON
{"type":"config","name":"latency-p95-chat-completions","metricName":"p95_ms","metricUnit":"ms","bestDirection":"lower"}
|
|
{"run":1,"commit":"ceed0e5","metric":941.252,"metrics":{"p50_ms":908.457,"mean_ms":917.123,"completion_tps_mean":52.427,"success_count":7},"status":"keep","description":"baseline","timestamp":1774557130,"segment":0}
|
|
{"run":2,"commit":"5269f43","metric":1032.315,"metrics":{"p50_ms":1020.402,"mean_ms":1011.466,"completion_tps_mean":47.671,"success_count":7},"status":"discard","description":"use stack buffer for token detokenization","timestamp":1774557493,"segment":0}
|
|
{"run":3,"commit":"994e607","metric":1004.435,"metrics":{"p50_ms":998.919,"mean_ms":990.771,"completion_tps_mean":48.528,"success_count":7},"status":"discard","description":"slim turbo4b runtime profile","timestamp":1774557635,"segment":0}
|
|
{"run":4,"commit":"db92212","metric":3027.145,"metrics":{"p50_ms":974.937,"mean_ms":1467.026,"completion_tps_mean":41.360,"success_count":7},"status":"discard","description":"switch to qwen-style chat template","timestamp":1774558217,"segment":0}
|
|
{"run":5,"commit":"caf4654","metric":965.663,"metrics":{"p50_ms":877.030,"mean_ms":897.251,"completion_tps_mean":53.686,"success_count":7},"status":"discard","description":"stop generation on default turn boundaries","timestamp":1774558444,"segment":0}
|
|
{"run":6,"commit":"e8402d2","metric":925.587,"metrics":{"p50_ms":893.913,"mean_ms":899.895,"completion_tps_mean":53.618,"success_count":7},"status":"keep","description":"disable llama perf counters in hot path","timestamp":1774558642,"segment":0}
|
|
{"type":"config","name":"dynamic-chat-templates","metricName":"template_score","metricUnit":"%","bestDirection":"higher"}
|
|
{"run":7,"commit":"89ef220","metric":20.0,"metrics":{"passed_cases":1,"failed_cases":4,"total_cases":5},"status":"keep","description":"baseline","timestamp":1774559683,"segment":1}
|