================================================
MLPerf Results Summary
================================================
SUT name : PySUT
Scenario : Server
Mode     : PerformanceOnly
Completed samples per second    : 76.92
Completed tokens per second: 100629.85
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 : 79.47
Min latency (ns)                : 11421034595
Max latency (ns)                : 137628593766
Mean latency (ns)               : 58818691399
50.00 percentile latency (ns)   : 58707577315
90.00 percentile latency (ns)   : 76066874875
95.00 percentile latency (ns)   : 81466834350
97.00 percentile latency (ns)   : 85104827225
99.00 percentile latency (ns)   : 93063903969
99.90 percentile latency (ns)   : 112576590201

Completed tokens per second                 : 100629.85
Min First Token latency (ns)                : 33384288
Max First Token latency (ns)                : 821918239
Mean First Token latency (ns)               : 166074819
50.00 percentile first token latency (ns)   : 156617472
90.00 percentile first token latency (ns)   : 238550517
95.00 percentile first token latency (ns)   : 269822897
97.00 percentile first token latency (ns)   : 290860621
99.00 percentile first token latency (ns)   : 338713060
99.90 percentile first token latency (ns)   : 444751866

Min Time per Output Token (ns)                : 14864151
Max Time per Output Token (ns)                : 58831373
Mean Time per Output Token (ns)               : 44897381
50.00 percentile time to output token (ns)   : 47163369
90.00 percentile time to output token (ns)   : 48644622
95.00 percentile time to output token (ns)   : 49050826
97.00 percentile time to output token (ns)   : 49284588
99.00 percentile time to output token (ns)   : 49802841
99.90 percentile time to output token (ns)   : 50354994

================================================
Test Parameters Used
================================================
samples_per_query : 1
target_qps : 79
ttft_latency (ns): 3000000000
tpot_latency (ns): 80000000
max_async_queries : 0
min_duration (ms): 600000
max_duration (ms): 0
min_query_count : 25584
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 : 6396
accuracy_sample_count : 4395
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.
