Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LLM Inference on Long-Context LLM Inference Decode

0.13Latency (ms)

Reuse

-0.27162.43925.157.8608Dec 18, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
0.130.18--
2025.12
0.24-2.912.95
2025.12
0.7---
2025.12
0.71---
2025.12
0.821.15--
2025.12
0.921.3--
2025.12
5.33-4.14.08
2025.12
10.17-2.152.14