================================================
MLPerf Results Summary
================================================
SUT name : PySUT
Scenario : Server
Mode     : PerformanceOnly
Completed samples per second    : 530.42
Completed tokens per second: 2028031.16
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 : 639.93
Min latency (ns)                : 5176243827
Max latency (ns)                : 1350332645680
Mean latency (ns)               : 225094189811
50.00 percentile latency (ns)   : 129054225490
90.00 percentile latency (ns)   : 564416681429
95.00 percentile latency (ns)   : 766801942489
97.00 percentile latency (ns)   : 903463597225
99.00 percentile latency (ns)   : 1123392650812
99.90 percentile latency (ns)   : 1261376553964

Completed tokens per second                 : 2028031.16
Min First Token latency (ns)                : 172953082
Max First Token latency (ns)                : 12927609677
Mean First Token latency (ns)               : 522935654
50.00 percentile first token latency (ns)   : 492790793
90.00 percentile first token latency (ns)   : 768256847
95.00 percentile first token latency (ns)   : 837604325
97.00 percentile first token latency (ns)   : 875828445
99.00 percentile first token latency (ns)   : 969502207
99.90 percentile first token latency (ns)   : 5535174637

Min Time per Output Token (ns)                : 31149388
Max Time per Output Token (ns)                : 305409030
Mean Time per Output Token (ns)               : 59984112
50.00 percentile time to output token (ns)   : 60983370
90.00 percentile time to output token (ns)   : 72041130
95.00 percentile time to output token (ns)   : 73215767
97.00 percentile time to output token (ns)   : 74025889
99.00 percentile time to output token (ns)   : 76564557
99.90 percentile time to output token (ns)   : 81168430

================================================
Test Parameters Used
================================================
samples_per_query : 1
target_qps : 640
ttft_latency (ns): 2000000000
tpot_latency (ns): 80000000
max_async_queries : 0
min_duration (ms): 600000
max_duration (ms): 0
min_query_count : 947808
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.
