Round score
—
concurrency warmup failed: candidate-5/rep0/hf-005: completions HTTP 500 from http://172.18.0.2:8000/v1/completions: Internal Server Error
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.
No prompt scores
concurrency warmup failed: candidate-5/rep0/hf-005: completions HTTP 500 from http://172.18.0.2:8000/v1/completions: Internal Server Error
Image digest
Patch hash