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
Temperature range
Request concurrency
Tier scheduling
Output policy
Thinking
Context limit
The same eligible inputs and output ceilings apply to every engine. Candidates must emit at least 90% of baseline tokens per request; natural output lengths can affect tier completion time. Slots refill until the group drains and stay occupied through protocol completion. Baseline exclusions and final drain can reduce actual concurrency below the configured cap.
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.
28 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-001 | 721.49ms | 54.003s | 2820 | 42.41ms | 1379 gaps for 2820 tokens |
| hf-002 | 747.82ms | 66.607s | 3187 | 42.89ms | 1716 gaps for 3187 tokens |
| hf-003 | 736.83ms | 93.844s |
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 | 24.25 |
| 2 | 0.000s | C32 | 32 | 32 | 22.75 |
| 3 | 0.000s | C32 | 32 | 32 | 24.51 |
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 |
| 41.64ms |
| 2568 gaps for 5120 tokens |
| hf-005 | 736.24ms | 85.052s | 4448 | 41.91ms | 2264 gaps for 4448 tokens |
| hf-006 | 714.36ms | 88.265s | 4654 | 42.74ms | 2312 gaps for 4654 tokens |
| hf-007 | 715.68ms | 93.345s | 5120 | 42.68ms | 2470 gaps for 5120 tokens |
| hf-008 | 745.27ms | 101.636s | 5120 | 44.28ms | 2856 gaps for 5120 tokens |
| hf-009 | 739.90ms | 71.222s | 3986 | 41.66ms | 1866 gaps for 3986 tokens |
| hf-010 | 729.81ms | 81.629s | 2745 | 41.91ms | 2163 gaps for 2745 tokens |
| hf-011 | 716.55ms | 59.760s | 3482 | 43.52ms | 1513 gaps for 3482 tokens |
| hf-012 | 734.92ms | 97.298s | 5120 | 41.88ms | 2721 gaps for 5120 tokens |
| hf-013 | 709.33ms | 100.645s | 4491 | 43.16ms | 2755 gaps for 4491 tokens |
| hf-014 | 746.45ms | 90.932s | 5120 | 43.97ms | 2421 gaps for 5120 tokens |
| hf-015 | 748.75ms | 96.383s | 5120 | 42.82ms | 2623 gaps for 5120 tokens |
| hf-016 | 713.85ms | 93.160s | 5120 | 42.98ms | 2464 gaps for 5120 tokens |
| hf-018 | 743.13ms | 74.478s | 4258 | 42.59ms | 1937 gaps for 4258 tokens |
| hf-019 | 710.06ms | 98.190s | 5120 | 43.58ms | 2655 gaps for 5120 tokens |
| hf-020 | 730.89ms | 90.847s | 5120 | 41.67ms | 2454 gaps for 5120 tokens |
| hf-021 | 733.19ms | 101.611s | 5120 | 41.64ms | 2957 gaps for 5120 tokens |
| hf-022 | 727.77ms | 43.656s | 2132 | 41.66ms | 1106 gaps for 2132 tokens |
| hf-023 | 712.34ms | 84.816s | 4400 | 43.48ms | 2211 gaps for 4400 tokens |
| hf-024 | 728.25ms | 70.160s | 3845 | 41.66ms | 1837 gaps for 3845 tokens |
| hf-025 | 735.74ms | 99.480s | 4162 | 42.70ms | 2754 gaps for 4162 tokens |
| hf-026 | 710.14ms | 51.272s | 2340 | 43.01ms | 1292 gaps for 2340 tokens |
| hf-027 | 736.32ms | 88.579s | 5120 | 50.33ms | 2345 gaps for 5120 tokens |
| hf-029 | 705.55ms | 83.522s | 4661 | 42.88ms | 2173 gaps for 4661 tokens |
| hf-030 | 734.56ms | 103.292s | 5120 | 61.06ms | 2959 gaps for 5120 tokens |
| hf-031 | 707.86ms | 48.003s | 2654 | 43.28ms | 1209 gaps for 2654 tokens |
| Top p |
|---|
| Seed |
|---|
| hf-017 | 1 | 0.791332 | 1 | 0 |
| hf-026 | 1 | 0.258588 | 1 | 0 |
| hf-001 | 1 | 0.732727 | 1 | 0 |
| hf-022 | 1 | 0.407771 | 1 | 0 |
| hf-002 | 1 | 0.711992 | 1 | 0 |
| hf-008 | 1 | 0.391391 | 1 | 0 |
| hf-000 | 1 | 0.432001 | 1 | 0 |
| hf-031 | 1 | 0.776567 | 1 | 0 |
| hf-024 | 1 | 0.995315 | 1 | 0 |
| hf-009 | 1 | 0.970461 | 1 | 0 |
| hf-011 | 1 | 0.8957 | 1 | 0 |
| hf-010 | 1 | 0.938026 | 1 | 0 |
| hf-028 | 1 | 0.489594 | 1 | 0 |
| hf-005 | 1 | 0.663059 | 1 | 0 |
| hf-018 | 1 | 0.737151 | 1 | 0 |
| hf-006 | 1 | 0.852864 | 1 | 0 |
| hf-016 | 1 | 0.996831 | 1 | 0 |
| hf-029 | 1 | 0.752413 | 1 | 0 |
| hf-014 | 1 | 0.690995 | 1 | 0 |
| hf-020 | 1 | 0.854241 | 1 | 0 |
| hf-004 | 1 | 0.647784 | 1 | 0 |
| hf-027 | 1 | 0.911383 | 1 | 0 |
| hf-023 | 1 | 0.502734 | 1 | 0 |
| hf-003 | 1 | 0.506793 | 1 | 0 |
| hf-019 | 1 | 0.450884 | 1 | 0 |
| hf-015 | 1 | 0.468658 | 1 | 0 |
| hf-012 | 1 | 0.444494 | 1 | 0 |
| hf-025 | 1 | 0.119657 | 1 | 0 |
| hf-021 | 1 | 0.295024 | 1 | 0 |
| hf-030 | 1 | 0.282037 | 1 | 0 |
| hf-013 | 1 | 0.234207 | 1 | 0 |
| hf-007 | 1 | 0.714609 | 1 | 0 |
| hf-004 | 2 | 0.647784 | 1 | 0 |
| hf-018 | 2 | 0.737151 | 1 | 0 |
| hf-031 | 2 | 0.776567 | 1 | 0 |
| hf-026 | 2 | 0.258588 | 1 | 0 |
| hf-028 | 2 | 0.489594 | 1 | 0 |
| hf-011 | 2 | 0.8957 | 1 | 0 |
| hf-024 | 2 | 0.995315 | 1 | 0 |
| hf-005 | 2 | 0.663059 | 1 | 0 |
| hf-009 | 2 | 0.970461 | 1 | 0 |
| hf-017 | 2 | 0.791332 | 1 | 0 |
| hf-027 | 2 | 0.911383 | 1 | 0 |
| hf-029 | 2 | 0.752413 | 1 | 0 |
| hf-023 | 2 | 0.502734 | 1 | 0 |
| hf-020 | 2 | 0.854241 | 1 | 0 |
| hf-006 | 2 | 0.852864 | 1 | 0 |
| hf-001 | 2 | 0.732727 | 1 | 0 |
| hf-003 | 2 | 0.506793 | 1 | 0 |
| hf-002 | 2 | 0.711992 | 1 | 0 |
| hf-016 | 2 | 0.996831 | 1 | 0 |
| hf-007 | 2 | 0.714609 | 1 | 0 |
| hf-014 | 2 | 0.690995 | 1 | 0 |
| hf-015 | 2 | 0.468658 | 1 | 0 |
| hf-019 | 2 | 0.450884 | 1 | 0 |
| hf-000 | 2 | 0.432001 | 1 | 0 |
| hf-012 | 2 | 0.444494 | 1 | 0 |
| hf-013 | 2 | 0.234207 | 1 | 0 |
| hf-022 | 2 | 0.407771 | 1 | 0 |
| hf-008 | 2 | 0.391391 | 1 | 0 |
| hf-021 | 2 | 0.295024 | 1 | 0 |
| hf-030 | 2 | 0.282037 | 1 | 0 |
| hf-025 | 2 | 0.119657 | 1 | 0 |
| hf-010 | 2 | 0.938026 | 1 | 0 |
| hf-000 | 3 | 0.432001 | 1 | 0 |
| hf-011 | 3 | 0.8957 | 1 | 0 |
| hf-007 | 3 | 0.714609 | 1 | 0 |
| hf-022 | 3 | 0.407771 | 1 | 0 |
| hf-031 | 3 | 0.776567 | 1 | 0 |
| hf-001 | 3 | 0.732727 | 1 | 0 |
| hf-010 | 3 | 0.938026 | 1 | 0 |
| hf-002 | 3 | 0.711992 | 1 | 0 |
| hf-009 | 3 | 0.970461 | 1 | 0 |
| hf-018 | 3 | 0.737151 | 1 | 0 |
| hf-029 | 3 | 0.752413 | 1 | 0 |
| hf-023 | 3 | 0.502734 | 1 | 0 |
| hf-013 | 3 | 0.234207 | 1 | 0 |
| hf-027 | 3 | 0.911383 | 1 | 0 |
| hf-005 | 3 | 0.663059 | 1 | 0 |
| hf-017 | 3 | 0.791332 | 1 | 0 |
| hf-006 | 3 | 0.852864 | 1 | 0 |
| hf-012 | 3 | 0.444494 | 1 | 0 |
| hf-014 | 3 | 0.690995 | 1 | 0 |
| hf-020 | 3 | 0.854241 | 1 | 0 |
| hf-024 | 3 | 0.995315 | 1 | 0 |
| hf-016 | 3 | 0.996831 | 1 | 0 |
| hf-015 | 3 | 0.468658 | 1 | 0 |
| hf-028 | 3 | 0.489594 | 1 | 0 |
| hf-003 | 3 | 0.506793 | 1 | 0 |
| hf-025 | 3 | 0.119657 | 1 | 0 |
| hf-021 | 3 | 0.295024 | 1 | 0 |
| hf-004 | 3 | 0.647784 | 1 | 0 |
| hf-008 | 3 | 0.391391 | 1 | 0 |
| hf-030 | 3 | 0.282037 | 1 | 0 |
| hf-026 | 3 | 0.258588 | 1 | 0 |
| hf-019 | 3 | 0.450884 | 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