Efficiency Evaluation on MATH 500 (Advanced Mathematical Problem Solving)
217.22Output ThroughputOur approach
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Our approachVocabulary size=13264, Hardware=Single A100-80G GPU, Target Model=Llama-3.1-8B-Instruct, Inference Engine=SGLang, Framework=SpecForge2026.03 | 217.22 | 5.1 | |
| 128k-vocabVocabulary size=128k, Hardware=Single A100-80G GPU, Target Model=Llama-3.1-8B-Instruct, Inference Engine=SGLang, Framework=SpecForge2026.03 | 206.74 | — |