================================================
MLPerf Results Summary
================================================
SUT name : PySUT
Scenario : Server
Mode     : PerformanceOnly
Completed samples per second    : 364.12
Completed tokens per second: 103274.69
Result is : VALID
  Performance constraints satisfied : Yes
  Min duration satisfied : Yes
  Min queries satisfied : Yes
  Early stopping satisfied: Yes
TTFT Early Stopping Result:
 * Run successful.
TPOT Early Stopping Result:
 * Run successful.

================================================
Additional Stats
================================================
Scheduled samples per second : 367.40
Min latency (ns)                : 212089241
Max latency (ns)                : 152884987698
Mean latency (ns)               : 36592061755
50.00 percentile latency (ns)   : 31817019141
90.00 percentile latency (ns)   : 66314734675
95.00 percentile latency (ns)   : 81635067850
97.00 percentile latency (ns)   : 93306674721
99.00 percentile latency (ns)   : 120420966784
99.90 percentile latency (ns)   : 143038539687

Completed tokens per second                 : 103274.69
Min First Token latency (ns)                : 48355874
Max First Token latency (ns)                : 1870250288
Mean First Token latency (ns)               : 557247300
50.00 percentile first token latency (ns)   : 554706074
90.00 percentile first token latency (ns)   : 770633382
95.00 percentile first token latency (ns)   : 878525506
97.00 percentile first token latency (ns)   : 988247277
99.00 percentile first token latency (ns)   : 1175800773
99.90 percentile first token latency (ns)   : 1472467190

Min Time per Output Token (ns)                : 77093
Max Time per Output Token (ns)                : 234735574
Mean Time per Output Token (ns)               : 127584163
50.00 percentile time to output token (ns)   : 128725129
90.00 percentile time to output token (ns)   : 141230290
95.00 percentile time to output token (ns)   : 144909979
97.00 percentile time to output token (ns)   : 146746876
99.00 percentile time to output token (ns)   : 149535693
99.90 percentile time to output token (ns)   : 154667428

================================================
Test Parameters Used
================================================
samples_per_query : 1
target_qps : 367
ttft_latency (ns): 2000000000
tpot_latency (ns): 200000000
max_async_queries : 0
min_duration (ms): 1800000
max_duration (ms): 0
min_query_count : 100
max_query_count : 0
qsl_rng_seed : 2085463073848966840
sample_index_rng_seed : 2747215439041700203
schedule_rng_seed : 16159082839903944936
accuracy_log_rng_seed : 0
accuracy_log_probability : 0
accuracy_log_sampling_target : 0
print_timestamps : 0
performance_issue_unique : 0
performance_issue_same : 0
performance_issue_same_index : 0
performance_sample_count : 24576
accuracy_sample_count : 24576
WARNING: sample_concatenate_permutation was set to true. 
Generated samples per query might be different as the one in the setting.
Check the generated_samples_per_query line in the detailed log for the real
samples_per_query value

No warnings encountered during test.

No errors encountered during test.
