List your company

Decoding Speedup on LongBench

1.64Decoding SpeedupPRR
1.24481.34741.451.5526Jun 29, 2026

Evaluation results

MethodLinks
PRRModel=GLM-4, DSA mechanism=InfLLM-v22026.061.64
PRRModel=GLM-Z1, DSA mechanism=InfLLM-v22026.061.61
PRRModel=Qwen3-14B, DSA mechanism=InfLLM-v22026.061.56
PRRModel=GLM-4, DSA mechanism=Quest2026.061.5
PRRModel=GLM-Z1, DSA mechanism=Quest2026.061.48
PRRModel=Qwen3-14B, DSA mechanism=Quest2026.061.44
PRRModel=DeepSeek-R1, DSA mechanism=Quest2026.061.39
PRRModel=Llama3, DSA mechanism=Quest2026.061.36
PRRModel=Qwen3-32B, DSA mechanism=InfLLM-v22026.061.35
PRRModel=Llama3, DSA mechanism=InfLLM-v22026.061.32
PRRModel=DeepSeek-R1, DSA mechanism=InfLLM-v22026.061.3
PRRModel=Qwen3-32B, DSA mechanism=Quest2026.061.26