================================================
MLPerf Results Summary
================================================
SUT name : PySUT
Scenario : Server
Mode     : PerformanceOnly
Completed samples per second    : 391.79
Completed tokens per second: 106949.36
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 : 396.45
Min latency (ns)                : 177655096
Max latency (ns)                : 159022928928
Mean latency (ns)               : 35027784597
50.00 percentile latency (ns)   : 29665157478
90.00 percentile latency (ns)   : 65354042582
95.00 percentile latency (ns)   : 81445389698
97.00 percentile latency (ns)   : 94720062134
99.00 percentile latency (ns)   : 121779059691
99.90 percentile latency (ns)   : 153518090042

Completed tokens per second                 : 106949.36
Min First Token latency (ns)                : 29691702
Max First Token latency (ns)                : 645252015
Mean First Token latency (ns)               : 338171935
50.00 percentile first token latency (ns)   : 341066505
90.00 percentile first token latency (ns)   : 432012091
95.00 percentile first token latency (ns)   : 452270713
97.00 percentile first token latency (ns)   : 463189349
99.00 percentile first token latency (ns)   : 480656211
99.90 percentile first token latency (ns)   : 508103923

Min Time per Output Token (ns)                : 19320711
Max Time per Output Token (ns)                : 179424841
Mean Time per Output Token (ns)               : 127532833
50.00 percentile time to output token (ns)   : 128993206
90.00 percentile time to output token (ns)   : 151844884
95.00 percentile time to output token (ns)   : 153433663
97.00 percentile time to output token (ns)   : 154097106
99.00 percentile time to output token (ns)   : 155357236
99.90 percentile time to output token (ns)   : 156785773

================================================
Test Parameters Used
================================================
samples_per_query : 1
target_qps : 396
ttft_latency (ns): 2000000000
tpot_latency (ns): 200000000
max_async_queries : 0
min_duration (ms): 1200000
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.
