At the tested reduced FIXED-K budgets, prefill and decode throughput improve on both vLLM and HF Transformers, with all per-model ratios reported in Table 2.

At the tested reduced FIXED-K budgets, prefill and decode throughput improve on both vLLM and HF Transformers, with all per-model ratios reported in Table 2. · CiteArk

Measurement results

0/28 assessed

0 supported0 disputed or conflicting28 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
printedValue: 8	8 experts	—	Not assessed
printedValue: 5	5 experts	—	Not assessed
printedValue: 0.63	0.63 ratio	—	Not assessed
printedValue: 1.15	1.15 times unpruned	—	Not assessed
printedValue: 1.18	1.18 times unpruned	—	Not assessed
printedValue: 1.26	1.26 times unpruned	—	Not assessed
printedValue: 1.70	1.7 times unpruned	—	Not assessed
printedValue: 10	10 experts	—	Not assessed
printedValue: 6	6 experts	—	Not assessed
printedValue: 0.60	0.6 ratio	—	Not assessed
printedValue: 1.25	1.25 times unpruned	—	Not assessed
printedValue: 1.65	1.65 times unpruned	—	Not assessed

At the tested reduced FIXED-K budgets, prefill and decode throughput improve on both vLLM and HF Transformers, with all per-model ratios reported in Table 2.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results