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.
27 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 1.832s | 74.993s | 3056 | 363.13ms | 1562 gaps for 3056 tokens |
| hf-001 | 1.906s | 76.598s | 4538 | 346.74ms | 1634 gaps for 4538 tokens |
| hf-002 | 1.970s | 112.183s |
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 | 25.22 |
| 2 | 0.000s | C32 | 32 | 32 | 23.67 |
| 3 | 0.000s | C32 | 32 | 32 | 25.84 |
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 |
|---|
| 5120 |
| 327.84ms |
| 2725 gaps for 5120 tokens |
| hf-003 | 869.53ms | 105.755s | 5120 | 1.429s | 2418 gaps for 5120 tokens |
| hf-004 | 1.826s | 103.696s | 4679 | 361.71ms | 2286 gaps for 4679 tokens |
| hf-006 | 1.960s | 104.825s | 5120 | 326.13ms | 2379 gaps for 5120 tokens |
| hf-007 | 1.965s | 100.522s | 4196 | 327.32ms | 2223 gaps for 4196 tokens |
| hf-008 | 1.963s | 102.710s | 4828 | 326.07ms | 2300 gaps for 4828 tokens |
| hf-009 | 1.906s | 84.261s | 3310 | 346.25ms | 1826 gaps for 3310 tokens |
| hf-010 | 2.142s | 65.872s | 3013 | 52.21ms | 1364 gaps for 3013 tokens |
| hf-011 | 2.108s | 96.354s | 3469 | 52.73ms | 2078 gaps for 3469 tokens |
| hf-012 | 2.139s | 114.896s | 4859 | 53.11ms | 2776 gaps for 4859 tokens |
| hf-013 | 2.244s | 91.811s | 5120 | 55.42ms | 1962 gaps for 5120 tokens |
| hf-014 | 2.102s | 94.831s | 5120 | 52.71ms | 2038 gaps for 5120 tokens |
| hf-015 | 2.239s | 75.024s | 2761 | 55.15ms | 1560 gaps for 2761 tokens |
| hf-017 | 2.243s | 79.455s | 4094 | 55.59ms | 1659 gaps for 4094 tokens |
| hf-018 | 2.233s | 78.641s | 3790 | 55.16ms | 1640 gaps for 3790 tokens |
| hf-019 | 2.189s | 107.189s | 5120 | 53.53ms | 2649 gaps for 5120 tokens |
| hf-021 | 2.097s | 105.681s | 4460 | 52.73ms | 2358 gaps for 4460 tokens |
| hf-024 | 2.091s | 97.765s | 4063 | 52.60ms | 2118 gaps for 4063 tokens |
| hf-025 | 2.235s | 104.508s | 4297 | 55.12ms | 2367 gaps for 4297 tokens |
| hf-026 | 2.230s | 85.654s | 3948 | 55.15ms | 1810 gaps for 3948 tokens |
| hf-027 | 2.222s | 114.437s | 5120 | 55.14ms | 2876 gaps for 5120 tokens |
| hf-028 | 2.188s | 88.629s | 4078 | 53.51ms | 1950 gaps for 4078 tokens |
| hf-029 | 2.233s | 91.004s | 5120 | 55.14ms | 1942 gaps for 5120 tokens |
| hf-030 | 2.096s | 85.119s | 3366 | 52.68ms | 1797 gaps for 3366 tokens |
| hf-031 | 2.187s | 83.281s | 3792 | 53.51ms | 1800 gaps for 3792 tokens |
| Top p |
|---|
| Seed |
|---|
| hf-004 | 1 | 0.374735 | 1 | 0 |
| hf-005 | 1 | 0.579075 | 1 | 0 |
| hf-020 | 1 | 0.61012 | 1 | 0 |
| hf-001 | 1 | 0.987002 | 1 | 0 |
| hf-015 | 1 | 0.197416 | 1 | 0 |
| hf-028 | 1 | 0.506323 | 1 | 0 |
| hf-010 | 1 | 0.955022 | 1 | 0 |
| hf-018 | 1 | 0.925935 | 1 | 0 |
| hf-022 | 1 | 0.497241 | 1 | 0 |
| hf-017 | 1 | 0.880366 | 1 | 0 |
| hf-026 | 1 | 0.6188 | 1 | 0 |
| hf-019 | 1 | 0.26784 | 1 | 0 |
| hf-029 | 1 | 0.91998 | 1 | 0 |
| hf-016 | 1 | 0.843568 | 1 | 0 |
| hf-013 | 1 | 0.755164 | 1 | 0 |
| hf-014 | 1 | 0.826373 | 1 | 0 |
| hf-021 | 1 | 0.303212 | 1 | 0 |
| hf-009 | 1 | 0.197127 | 1 | 0 |
| hf-011 | 1 | 0.239254 | 1 | 0 |
| hf-000 | 1 | 1.005729 | 1 | 0 |
| hf-023 | 1 | 0.975986 | 1 | 0 |
| hf-007 | 1 | 0.267166 | 1 | 0 |
| hf-008 | 1 | 0.276091 | 1 | 0 |
| hf-031 | 1 | 0.952171 | 1 | 0 |
| hf-025 | 1 | 0.139681 | 1 | 0 |
| hf-006 | 1 | 0.561965 | 1 | 0 |
| hf-003 | 1 | 0.24968 | 1 | 0 |
| hf-030 | 1 | 0.378947 | 1 | 0 |
| hf-002 | 1 | 0.322905 | 1 | 0 |
| hf-024 | 1 | 0.382038 | 1 | 0 |
| hf-027 | 1 | 0.15659 | 1 | 0 |
| hf-012 | 1 | 0.116817 | 1 | 0 |
| hf-005 | 2 | 0.579075 | 1 | 0 |
| hf-020 | 2 | 0.61012 | 1 | 0 |
| hf-010 | 2 | 0.955022 | 1 | 0 |
| hf-015 | 2 | 0.197416 | 1 | 0 |
| hf-030 | 2 | 0.378947 | 1 | 0 |
| hf-023 | 2 | 0.975986 | 1 | 0 |
| hf-024 | 2 | 0.382038 | 1 | 0 |
| hf-000 | 2 | 1.005729 | 1 | 0 |
| hf-008 | 2 | 0.276091 | 1 | 0 |
| hf-017 | 2 | 0.880366 | 1 | 0 |
| hf-001 | 2 | 0.987002 | 1 | 0 |
| hf-007 | 2 | 0.267166 | 1 | 0 |
| hf-013 | 2 | 0.755164 | 1 | 0 |
| hf-026 | 2 | 0.6188 | 1 | 0 |
| hf-031 | 2 | 0.952171 | 1 | 0 |
| hf-018 | 2 | 0.925935 | 1 | 0 |
| hf-009 | 2 | 0.197127 | 1 | 0 |
| hf-022 | 2 | 0.497241 | 1 | 0 |
| hf-028 | 2 | 0.506323 | 1 | 0 |
| hf-016 | 2 | 0.843568 | 1 | 0 |
| hf-029 | 2 | 0.91998 | 1 | 0 |
| hf-014 | 2 | 0.826373 | 1 | 0 |
| hf-025 | 2 | 0.139681 | 1 | 0 |
| hf-006 | 2 | 0.561965 | 1 | 0 |
| hf-003 | 2 | 0.24968 | 1 | 0 |
| hf-011 | 2 | 0.239254 | 1 | 0 |
| hf-012 | 2 | 0.116817 | 1 | 0 |
| hf-004 | 2 | 0.374735 | 1 | 0 |
| hf-021 | 2 | 0.303212 | 1 | 0 |
| hf-002 | 2 | 0.322905 | 1 | 0 |
| hf-019 | 2 | 0.26784 | 1 | 0 |
| hf-027 | 2 | 0.15659 | 1 | 0 |
| hf-018 | 3 | 0.925935 | 1 | 0 |
| hf-031 | 3 | 0.952171 | 1 | 0 |
| hf-010 | 3 | 0.955022 | 1 | 0 |
| hf-022 | 3 | 0.497241 | 1 | 0 |
| hf-000 | 3 | 1.005729 | 1 | 0 |
| hf-029 | 3 | 0.91998 | 1 | 0 |
| hf-023 | 3 | 0.975986 | 1 | 0 |
| hf-009 | 3 | 0.197127 | 1 | 0 |
| hf-001 | 3 | 0.987002 | 1 | 0 |
| hf-030 | 3 | 0.378947 | 1 | 0 |
| hf-016 | 3 | 0.843568 | 1 | 0 |
| hf-017 | 3 | 0.880366 | 1 | 0 |
| hf-026 | 3 | 0.6188 | 1 | 0 |
| hf-013 | 3 | 0.755164 | 1 | 0 |
| hf-014 | 3 | 0.826373 | 1 | 0 |
| hf-011 | 3 | 0.239254 | 1 | 0 |
| hf-024 | 3 | 0.382038 | 1 | 0 |
| hf-028 | 3 | 0.506323 | 1 | 0 |
| hf-005 | 3 | 0.579075 | 1 | 0 |
| hf-020 | 3 | 0.61012 | 1 | 0 |
| hf-007 | 3 | 0.267166 | 1 | 0 |
| hf-004 | 3 | 0.374735 | 1 | 0 |
| hf-006 | 3 | 0.561965 | 1 | 0 |
| hf-021 | 3 | 0.303212 | 1 | 0 |
| hf-008 | 3 | 0.276091 | 1 | 0 |
| hf-015 | 3 | 0.197416 | 1 | 0 |
| hf-003 | 3 | 0.24968 | 1 | 0 |
| hf-002 | 3 | 0.322905 | 1 | 0 |
| hf-019 | 3 | 0.26784 | 1 | 0 |
| hf-012 | 3 | 0.116817 | 1 | 0 |
| hf-025 | 3 | 0.139681 | 1 | 0 |
| hf-027 | 3 | 0.15659 | 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