List your company

End-to-end single-step decoding on DeepSeek-R1-Distill-LLaMA-8B 16K Context

23Latency (ms)LessIsMore
22.90823.52924.1524.771Aug 9, 2025

Evaluation results

MethodLinks
LessIsMoreToken Budget=2K, Serving Stack=SGLang + FlashInfer, Hardware=NVIDIA A5000 GPU2025.0823
QuestToken Budget=2K, Serving Stack=SGLang + FlashInfer, Hardware=NVIDIA A5000 GPU2025.0824.2
TidalDecodeToken Budget=2K, Serving Stack=SGLang + FlashInfer, Hardware=NVIDIA A5000 GPU2025.0824.3
Full AttentionToken Budget=2K, Serving Stack=SGLang + FlashInfer, Hardware=NVIDIA A5000 GPU2025.0825.3