Round score
0
weighted tier speedup after failure cap and deduction
Eligible requests
—
trusted baseline exclusions removed
Failed eligible requests
—
each request counted once
Raw weighted speedup
—
before failure cap and deduction
The round score uses weighted completion times for all eligible work in each tier. Per-request speedups below are diagnostics, not score contributions. Only trusted baseline exclusions are removed; candidate failures remain in the eligible count and incur the configured failure penalty.
Reference engine
The baseline is what candidates are measured against, so it has no speedup of its own. Its SLA replay is below.
31 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 1.931s | 90.118s | 4458 | 358.94ms | 1902 gaps for 4458 tokens |
| hf-001 | 2.048s | 91.901s | 3083 | 62.34ms | 1983 gaps for 3083 tokens |
| hf-002 | 1.927s | 105.681s |
Occupied client slots include protocol completion and final drain. Mean occupancy is weighted by elapsed time; it can be below the requested cap.
| Repetition | Group start | Requested | Effective cap | Peak | Mean |
|---|---|---|---|---|---|
| 1 | 0.000s | C32 | 32 | 32 | 25.85 |
| 2 | 0.000s | C32 | 32 | 32 | 25.30 |
| 3 | 0.000s | C32 | 32 | 32 | 27.15 |
Actual settings for each measured request. Each prompt keeps its temperature across repetitions and engines. Generation uses seed 0 throughout qualification, warmups and measured repetitions; fixed settings do not guarantee identical output text.
| Prompt | Repetition | Temperature |
|---|
| 4136 |
| 357.65ms |
| 2309 gaps for 4136 tokens |
| hf-003 | 886.17ms | 103.606s | 3968 | 1.537s | 2226 gaps for 3968 tokens |
| hf-004 | 2.019s | 72.926s | 3062 | 399.69ms | 1508 gaps for 3062 tokens |
| hf-005 | 2.015s | 101.466s | 5120 | 398.33ms | 2167 gaps for 5120 tokens |
| hf-006 | 2.042s | 87.238s | 4836 | 62.85ms | 1865 gaps for 4836 tokens |
| hf-007 | 2.241s | 108.378s | 5120 | 53.89ms | 2400 gaps for 5120 tokens |
| hf-009 | 2.039s | 92.472s | 5120 | 62.54ms | 1999 gaps for 5120 tokens |
| hf-010 | 2.015s | 106.155s | 4331 | 398.33ms | 2298 gaps for 4331 tokens |
| hf-011 | 2.235s | 114.898s | 5120 | 53.89ms | 2681 gaps for 5120 tokens |
| hf-012 | 2.359s | 87.291s | 4242 | 57.38ms | 1821 gaps for 4242 tokens |
| hf-013 | 2.240s | 112.133s | 5120 | 53.89ms | 2541 gaps for 5120 tokens |
| hf-014 | 2.069s | 111.266s | 4443 | 52.88ms | 2661 gaps for 4443 tokens |
| hf-015 | 2.069s | 110.586s | 5120 | 52.48ms | 2621 gaps for 5120 tokens |
| hf-016 | 2.233s | 67.485s | 3097 | 53.89ms | 1407 gaps for 3097 tokens |
| hf-017 | 2.234s | 90.307s | 5120 | 54.31ms | 1907 gaps for 5120 tokens |
| hf-018 | 2.066s | 111.887s | 5120 | 52.58ms | 2704 gaps for 5120 tokens |
| hf-019 | 2.229s | 79.178s | 3913 | 54.30ms | 1657 gaps for 3913 tokens |
| hf-020 | 2.229s | 87.772s | 3101 | 54.30ms | 1846 gaps for 3101 tokens |
| hf-021 | 2.230s | 92.921s | 3778 | 54.30ms | 1971 gaps for 3778 tokens |
| hf-022 | 2.357s | 93.732s | 3523 | 56.97ms | 1974 gaps for 3523 tokens |
| hf-023 | 2.353s | 79.051s | 4214 | 57.28ms | 1639 gaps for 4214 tokens |
| hf-024 | 2.222s | 103.441s | 5120 | 55.22ms | 2247 gaps for 5120 tokens |
| hf-025 | 2.356s | 82.414s | 4224 | 57.26ms | 1712 gaps for 4224 tokens |
| hf-026 | 2.355s | 104.505s | 5019 | 57.12ms | 2252 gaps for 5019 tokens |
| hf-027 | 2.219s | 101.791s | 5120 | 55.26ms | 2202 gaps for 5120 tokens |
| hf-028 | 2.052s | 109.215s | 5120 | 52.70ms | 2554 gaps for 5120 tokens |
| hf-029 | 2.317s | 80.342s | 4562 | 57.12ms | 1668 gaps for 4562 tokens |
| hf-030 | 2.319s | 110.638s | 5120 | 57.10ms | 2458 gaps for 5120 tokens |
| hf-031 | 2.216s | 110.024s | 5120 | 55.16ms | 2458 gaps for 5120 tokens |
| Top p |
|---|
| Seed |
|---|
| hf-008 | 1 | 0.702985 | 1 | 0 |
| hf-025 | 1 | 0.985364 | 1 | 0 |
| hf-016 | 1 | 0.477202 | 1 | 0 |
| hf-019 | 1 | 0.323977 | 1 | 0 |
| hf-001 | 1 | 0.145615 | 1 | 0 |
| hf-009 | 1 | 0.80922 | 1 | 0 |
| hf-006 | 1 | 0.806947 | 1 | 0 |
| hf-020 | 1 | 0.161701 | 1 | 0 |
| hf-000 | 1 | 0.751507 | 1 | 0 |
| hf-017 | 1 | 0.948598 | 1 | 0 |
| hf-012 | 1 | 0.971562 | 1 | 0 |
| hf-021 | 1 | 0.394709 | 1 | 0 |
| hf-023 | 1 | 0.836006 | 1 | 0 |
| hf-029 | 1 | 0.888902 | 1 | 0 |
| hf-022 | 1 | 0.135465 | 1 | 0 |
| hf-027 | 1 | 0.616175 | 1 | 0 |
| hf-018 | 1 | 0.582993 | 1 | 0 |
| hf-024 | 1 | 0.606986 | 1 | 0 |
| hf-004 | 1 | 0.705908 | 1 | 0 |
| hf-002 | 1 | 0.308187 | 1 | 0 |
| hf-026 | 1 | 0.634191 | 1 | 0 |
| hf-005 | 1 | 0.644584 | 1 | 0 |
| hf-007 | 1 | 0.526161 | 1 | 0 |
| hf-031 | 1 | 0.466727 | 1 | 0 |
| hf-015 | 1 | 0.422296 | 1 | 0 |
| hf-013 | 1 | 0.376028 | 1 | 0 |
| hf-030 | 1 | 0.466474 | 1 | 0 |
| hf-028 | 1 | 0.426835 | 1 | 0 |
| hf-011 | 1 | 0.229212 | 1 | 0 |
| hf-003 | 1 | 0.165866 | 1 | 0 |
| hf-014 | 1 | 0.234039 | 1 | 0 |
| hf-010 | 1 | 0.183241 | 1 | 0 |
| hf-012 | 2 | 0.971562 | 1 | 0 |
| hf-029 | 2 | 0.888902 | 1 | 0 |
| hf-021 | 2 | 0.394709 | 1 | 0 |
| hf-016 | 2 | 0.477202 | 1 | 0 |
| hf-019 | 2 | 0.323977 | 1 | 0 |
| hf-023 | 2 | 0.836006 | 1 | 0 |
| hf-004 | 2 | 0.705908 | 1 | 0 |
| hf-008 | 2 | 0.702985 | 1 | 0 |
| hf-022 | 2 | 0.135465 | 1 | 0 |
| hf-026 | 2 | 0.634191 | 1 | 0 |
| hf-020 | 2 | 0.161701 | 1 | 0 |
| hf-025 | 2 | 0.985364 | 1 | 0 |
| hf-006 | 2 | 0.806947 | 1 | 0 |
| hf-017 | 2 | 0.948598 | 1 | 0 |
| hf-002 | 2 | 0.308187 | 1 | 0 |
| hf-001 | 2 | 0.145615 | 1 | 0 |
| hf-009 | 2 | 0.80922 | 1 | 0 |
| hf-010 | 2 | 0.183241 | 1 | 0 |
| hf-027 | 2 | 0.616175 | 1 | 0 |
| hf-000 | 2 | 0.751507 | 1 | 0 |
| hf-005 | 2 | 0.644584 | 1 | 0 |
| hf-003 | 2 | 0.165866 | 1 | 0 |
| hf-024 | 2 | 0.606986 | 1 | 0 |
| hf-007 | 2 | 0.526161 | 1 | 0 |
| hf-031 | 2 | 0.466727 | 1 | 0 |
| hf-030 | 2 | 0.466474 | 1 | 0 |
| hf-028 | 2 | 0.426835 | 1 | 0 |
| hf-013 | 2 | 0.376028 | 1 | 0 |
| hf-015 | 2 | 0.422296 | 1 | 0 |
| hf-014 | 2 | 0.234039 | 1 | 0 |
| hf-018 | 2 | 0.582993 | 1 | 0 |
| hf-011 | 2 | 0.229212 | 1 | 0 |
| hf-004 | 3 | 0.705908 | 1 | 0 |
| hf-017 | 3 | 0.948598 | 1 | 0 |
| hf-000 | 3 | 0.751507 | 1 | 0 |
| hf-023 | 3 | 0.836006 | 1 | 0 |
| hf-029 | 3 | 0.888902 | 1 | 0 |
| hf-025 | 3 | 0.985364 | 1 | 0 |
| hf-028 | 3 | 0.426835 | 1 | 0 |
| hf-016 | 3 | 0.477202 | 1 | 0 |
| hf-012 | 3 | 0.971562 | 1 | 0 |
| hf-006 | 3 | 0.806947 | 1 | 0 |
| hf-014 | 3 | 0.234039 | 1 | 0 |
| hf-022 | 3 | 0.135465 | 1 | 0 |
| hf-009 | 3 | 0.80922 | 1 | 0 |
| hf-020 | 3 | 0.161701 | 1 | 0 |
| hf-008 | 3 | 0.702985 | 1 | 0 |
| hf-005 | 3 | 0.644584 | 1 | 0 |
| hf-003 | 3 | 0.165866 | 1 | 0 |
| hf-027 | 3 | 0.616175 | 1 | 0 |
| hf-026 | 3 | 0.634191 | 1 | 0 |
| hf-010 | 3 | 0.183241 | 1 | 0 |
| hf-019 | 3 | 0.323977 | 1 | 0 |
| hf-024 | 3 | 0.606986 | 1 | 0 |
| hf-007 | 3 | 0.526161 | 1 | 0 |
| hf-002 | 3 | 0.308187 | 1 | 0 |
| hf-031 | 3 | 0.466727 | 1 | 0 |
| hf-030 | 3 | 0.466474 | 1 | 0 |
| hf-001 | 3 | 0.145615 | 1 | 0 |
| hf-015 | 3 | 0.422296 | 1 | 0 |
| hf-018 | 3 | 0.582993 | 1 | 0 |
| hf-013 | 3 | 0.376028 | 1 | 0 |
| hf-021 | 3 | 0.394709 | 1 | 0 |
| hf-011 | 3 | 0.229212 | 1 | 0 |
role
evidence
request concurrency
requests per s
sla goodput ratio
output tokens per s
p99 e2e ms rel range
p99 itl ms rel range
p99 ttft ms rel range
tier completion max rel range
Image digest