================================================
MLPerf Results Summary
================================================
SUT name : PySUT
Scenario : Server
Mode     : PerformanceOnly
Completed samples per second    : 686.78
Completed tokens per second: 899005.11
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 : 700.10
Min latency (ns)                : 6840314384
Max latency (ns)                : 143892587548
Mean latency (ns)               : 49030397404
50.00 percentile latency (ns)   : 48669179216
90.00 percentile latency (ns)   : 62053495402
95.00 percentile latency (ns)   : 66446530008
97.00 percentile latency (ns)   : 69495405136
99.00 percentile latency (ns)   : 75851969833
99.90 percentile latency (ns)   : 90857839996

Completed tokens per second                 : 899005.11
Min First Token latency (ns)                : 31393777
Max First Token latency (ns)                : 1450292684
Mean First Token latency (ns)               : 140135498
50.00 percentile first token latency (ns)   : 130400037
90.00 percentile first token latency (ns)   : 201097114
95.00 percentile first token latency (ns)   : 228678800
97.00 percentile first token latency (ns)   : 248556841
99.00 percentile first token latency (ns)   : 290530557
99.90 percentile first token latency (ns)   : 537423176

Min Time per Output Token (ns)                : 10049209
Max Time per Output Token (ns)                : 64301567
Mean Time per Output Token (ns)               : 37387600
50.00 percentile time to output token (ns)   : 38036194
90.00 percentile time to output token (ns)   : 39322904
95.00 percentile time to output token (ns)   : 39777443
97.00 percentile time to output token (ns)   : 40058321
99.00 percentile time to output token (ns)   : 40587885
99.90 percentile time to output token (ns)   : 41349458

================================================
Test Parameters Used
================================================
samples_per_query : 1
target_qps : 700
ttft_latency (ns): 3000000000
tpot_latency (ns): 80000000
max_async_queries : 0
min_duration (ms): 1200000
max_duration (ms): 0
min_query_count : 460512
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.
