XPENG unveiled X-Cache, a plug-and-play world model accelerator that boosts AI inference speed by 2.7x without requiring training. The advancement demonstrates practical value for autonomous driving applications.
← News
Clean Energy Clean Energy Planet
XPENG Unveils The “World Model Accelerator” X-Cache, Which Requires No Training, Is Plug-And-Play, And Boosts Inference Speed By 2.7 Times
2.7 Times multiplier Inference speed improvement
None plug-and-play Training requirement
World Model Accelerator AI optimization Technology type
0% training required
2.7x inference speed boost