Competing risk analysis when proportional hazards assumption is not met

[kc]

I am using Fine-Gray subdistribution hazard model to analyze time to event in the presence of competing risks. But, it assumes proportional hazards for the subdistribution hazard and one of the important covariates doesn't meet this assumption. I am wondering how do I go about addressing this issue. Alternatively, to address the non-proportionality, we can use the accelerated failure time models (AFT). But, how do you adjust for competing risk in these models?

Any help (with code) would be greatly appreciated!

Thanks in advance.

[Ksharp]

https://communities.sas.com/t5/Statistical-Procedures/Dealing-with-nonproportionality-in-a-Cox-PH-Mo...

[kc]

Sorry if I am missing anything but this post/embedded links do not talk about the scenario where competing risks and non-proportionality are involved.