================================================
MLPerf Results Summary
================================================
SUT name : PySUT
Scenario : Server
Mode     : PerformanceOnly
Completed samples per second    : 17.70
Completed tokens per second: 67578.35
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 : 18.51
Min latency (ns)                : 7158685490
Max latency (ns)                : 1264739871456
Mean latency (ns)               : 227198017353
50.00 percentile latency (ns)   : 130075804433
90.00 percentile latency (ns)   : 571322660061
95.00 percentile latency (ns)   : 764363154694
97.00 percentile latency (ns)   : 900040897044
99.00 percentile latency (ns)   : 1137778868068
99.90 percentile latency (ns)   : 1263196156263

Completed tokens per second                 : 67578.35
Min First Token latency (ns)                : 179631562
Max First Token latency (ns)                : 1919591933
Mean First Token latency (ns)               : 514178864
50.00 percentile first token latency (ns)   : 490406133
90.00 percentile first token latency (ns)   : 778399719
95.00 percentile first token latency (ns)   : 850411760
97.00 percentile first token latency (ns)   : 889573354
99.00 percentile first token latency (ns)   : 985577332
99.90 percentile first token latency (ns)   : 1267436192

Min Time per Output Token (ns)                : 32797276
Max Time per Output Token (ns)                : 75127180
Mean Time per Output Token (ns)               : 60583582
50.00 percentile time to output token (ns)   : 61308160
90.00 percentile time to output token (ns)   : 72613897
95.00 percentile time to output token (ns)   : 73398488
97.00 percentile time to output token (ns)   : 73648998
99.00 percentile time to output token (ns)   : 73885145
99.90 percentile time to output token (ns)   : 74188983

================================================
Test Parameters Used
================================================
samples_per_query : 1
target_qps : 18.3333
ttft_latency (ns): 2000000000
tpot_latency (ns): 80000000
max_async_queries : 0
min_duration (ms): 600000
max_duration (ms): 0
min_query_count : 24378
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 : 4388
accuracy_sample_count : 4388
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.
