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.
29 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 962.03ms | 92.182s | 3121 | 1.314s | 1969 gaps for 3121 tokens |
| hf-001 | 2.129s | 111.456s | 5120 | 51.88ms | 2508 gaps for 5120 tokens |
| hf-002 | 2.186s | 111.481s |
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 | 24.91 |
| 2 | 0.000s | C32 | 32 | 32 | 25.45 |
| 3 | 0.000s | C32 | 32 | 32 | 26.03 |
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 |
| 83.97ms |
| 2505 gaps for 5120 tokens |
| hf-003 | 2.090s | 94.709s | 5120 | 330.05ms | 2026 gaps for 5120 tokens |
| hf-005 | 2.130s | 71.950s | 3472 | 51.62ms | 1500 gaps for 3472 tokens |
| hf-006 | 2.089s | 69.236s | 3326 | 330.11ms | 1437 gaps for 3326 tokens |
| hf-007 | 2.184s | 112.563s | 5120 | 85.82ms | 2543 gaps for 5120 tokens |
| hf-009 | 2.379s | 105.538s | 5120 | 55.41ms | 2304 gaps for 5120 tokens |
| hf-010 | 2.182s | 116.609s | 5120 | 84.11ms | 2709 gaps for 5120 tokens |
| hf-011 | 2.176s | 99.623s | 4306 | 84.23ms | 2160 gaps for 4306 tokens |
| hf-012 | 2.227s | 115.190s | 5120 | 52.20ms | 2645 gaps for 5120 tokens |
| hf-013 | 2.126s | 100.609s | 5120 | 52.78ms | 2197 gaps for 5120 tokens |
| hf-014 | 2.230s | 120.323s | 5120 | 51.99ms | 2928 gaps for 5120 tokens |
| hf-016 | 2.221s | 89.050s | 5120 | 52.04ms | 1894 gaps for 5120 tokens |
| hf-017 | 2.362s | 89.021s | 5120 | 55.41ms | 1889 gaps for 5120 tokens |
| hf-018 | 2.120s | 117.788s | 5120 | 52.68ms | 2754 gaps for 5120 tokens |
| hf-019 | 2.219s | 110.967s | 5120 | 52.02ms | 2489 gaps for 5120 tokens |
| hf-020 | 2.220s | 95.236s | 5120 | 52.03ms | 2046 gaps for 5120 tokens |
| hf-021 | 2.109s | 109.274s | 5120 | 52.33ms | 2438 gaps for 5120 tokens |
| hf-022 | 2.226s | 74.262s | 4240 | 52.10ms | 1567 gaps for 4240 tokens |
| hf-023 | 2.117s | 112.455s | 5120 | 52.42ms | 2544 gaps for 5120 tokens |
| hf-024 | 2.215s | 121.283s | 5120 | 52.03ms | 3012 gaps for 5120 tokens |
| hf-025 | 2.212s | 116.790s | 5120 | 52.06ms | 2720 gaps for 5120 tokens |
| hf-026 | 2.114s | 116.530s | 5120 | 52.45ms | 2695 gaps for 5120 tokens |
| hf-027 | 2.347s | 68.463s | 3420 | 56.09ms | 1421 gaps for 3420 tokens |
| hf-028 | 2.221s | 114.800s | 4636 | 52.01ms | 2629 gaps for 4636 tokens |
| hf-029 | 2.344s | 117.540s | 5120 | 56.34ms | 2665 gaps for 5120 tokens |
| hf-030 | 2.115s | 77.028s | 3262 | 52.42ms | 1614 gaps for 3262 tokens |
| hf-031 | 2.111s | 121.616s | 5120 | 52.34ms | 3012 gaps for 5120 tokens |
| Top p |
|---|
| Seed |
|---|
| hf-004 | 1 | 0.945034 | 1 | 0 |
| hf-015 | 1 | 0.901402 | 1 | 0 |
| hf-001 | 1 | 0.444844 | 1 | 0 |
| hf-030 | 1 | 0.476485 | 1 | 0 |
| hf-022 | 1 | 0.985248 | 1 | 0 |
| hf-006 | 1 | 0.8152 | 1 | 0 |
| hf-027 | 1 | 0.901469 | 1 | 0 |
| hf-017 | 1 | 0.913776 | 1 | 0 |
| hf-016 | 1 | 0.940146 | 1 | 0 |
| hf-013 | 1 | 0.726073 | 1 | 0 |
| hf-000 | 1 | 0.101237 | 1 | 0 |
| hf-021 | 1 | 0.504238 | 1 | 0 |
| hf-020 | 1 | 0.921463 | 1 | 0 |
| hf-003 | 1 | 0.740817 | 1 | 0 |
| hf-005 | 1 | 0.760143 | 1 | 0 |
| hf-011 | 1 | 0.548234 | 1 | 0 |
| hf-029 | 1 | 0.316805 | 1 | 0 |
| hf-008 | 1 | 0.827812 | 1 | 0 |
| hf-009 | 1 | 0.602937 | 1 | 0 |
| hf-018 | 1 | 0.221058 | 1 | 0 |
| hf-019 | 1 | 0.382532 | 1 | 0 |
| hf-002 | 1 | 0.426332 | 1 | 0 |
| hf-007 | 1 | 0.412296 | 1 | 0 |
| hf-023 | 1 | 0.485263 | 1 | 0 |
| hf-028 | 1 | 0.165048 | 1 | 0 |
| hf-012 | 1 | 0.350242 | 1 | 0 |
| hf-026 | 1 | 0.240206 | 1 | 0 |
| hf-010 | 1 | 0.319315 | 1 | 0 |
| hf-025 | 1 | 0.298822 | 1 | 0 |
| hf-031 | 1 | 0.106656 | 1 | 0 |
| hf-014 | 1 | 0.248189 | 1 | 0 |
| hf-024 | 1 | 0.121643 | 1 | 0 |
| hf-022 | 2 | 0.985248 | 1 | 0 |
| hf-006 | 2 | 0.8152 | 1 | 0 |
| hf-027 | 2 | 0.901469 | 1 | 0 |
| hf-011 | 2 | 0.548234 | 1 | 0 |
| hf-007 | 2 | 0.412296 | 1 | 0 |
| hf-005 | 2 | 0.760143 | 1 | 0 |
| hf-008 | 2 | 0.827812 | 1 | 0 |
| hf-030 | 2 | 0.476485 | 1 | 0 |
| hf-016 | 2 | 0.940146 | 1 | 0 |
| hf-015 | 2 | 0.901402 | 1 | 0 |
| hf-020 | 2 | 0.921463 | 1 | 0 |
| hf-003 | 2 | 0.740817 | 1 | 0 |
| hf-004 | 2 | 0.945034 | 1 | 0 |
| hf-017 | 2 | 0.913776 | 1 | 0 |
| hf-013 | 2 | 0.726073 | 1 | 0 |
| hf-000 | 2 | 0.101237 | 1 | 0 |
| hf-009 | 2 | 0.602937 | 1 | 0 |
| hf-028 | 2 | 0.165048 | 1 | 0 |
| hf-019 | 2 | 0.382532 | 1 | 0 |
| hf-021 | 2 | 0.504238 | 1 | 0 |
| hf-002 | 2 | 0.426332 | 1 | 0 |
| hf-001 | 2 | 0.444844 | 1 | 0 |
| hf-023 | 2 | 0.485263 | 1 | 0 |
| hf-012 | 2 | 0.350242 | 1 | 0 |
| hf-025 | 2 | 0.298822 | 1 | 0 |
| hf-010 | 2 | 0.319315 | 1 | 0 |
| hf-026 | 2 | 0.240206 | 1 | 0 |
| hf-029 | 2 | 0.316805 | 1 | 0 |
| hf-018 | 2 | 0.221058 | 1 | 0 |
| hf-014 | 2 | 0.248189 | 1 | 0 |
| hf-031 | 2 | 0.106656 | 1 | 0 |
| hf-024 | 2 | 0.121643 | 1 | 0 |
| hf-005 | 3 | 0.760143 | 1 | 0 |
| hf-015 | 3 | 0.901402 | 1 | 0 |
| hf-008 | 3 | 0.827812 | 1 | 0 |
| hf-027 | 3 | 0.901469 | 1 | 0 |
| hf-006 | 3 | 0.8152 | 1 | 0 |
| hf-022 | 3 | 0.985248 | 1 | 0 |
| hf-024 | 3 | 0.121643 | 1 | 0 |
| hf-000 | 3 | 0.101237 | 1 | 0 |
| hf-004 | 3 | 0.945034 | 1 | 0 |
| hf-017 | 3 | 0.913776 | 1 | 0 |
| hf-016 | 3 | 0.940146 | 1 | 0 |
| hf-003 | 3 | 0.740817 | 1 | 0 |
| hf-020 | 3 | 0.921463 | 1 | 0 |
| hf-013 | 3 | 0.726073 | 1 | 0 |
| hf-030 | 3 | 0.476485 | 1 | 0 |
| hf-009 | 3 | 0.602937 | 1 | 0 |
| hf-023 | 3 | 0.485263 | 1 | 0 |
| hf-001 | 3 | 0.444844 | 1 | 0 |
| hf-011 | 3 | 0.548234 | 1 | 0 |
| hf-007 | 3 | 0.412296 | 1 | 0 |
| hf-021 | 3 | 0.504238 | 1 | 0 |
| hf-002 | 3 | 0.426332 | 1 | 0 |
| hf-019 | 3 | 0.382532 | 1 | 0 |
| hf-026 | 3 | 0.240206 | 1 | 0 |
| hf-029 | 3 | 0.316805 | 1 | 0 |
| hf-012 | 3 | 0.350242 | 1 | 0 |
| hf-028 | 3 | 0.165048 | 1 | 0 |
| hf-025 | 3 | 0.298822 | 1 | 0 |
| hf-010 | 3 | 0.319315 | 1 | 0 |
| hf-018 | 3 | 0.221058 | 1 | 0 |
| hf-014 | 3 | 0.248189 | 1 | 0 |
| hf-031 | 3 | 0.106656 | 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