[Quant] X86 qengine always uses fbgemm kernels on OS other than Linux (#93218)
**Summary**
X86 quantization backend (qengine) with oneDNN kernels has not been validated on OS other than Linux. So, let it fall back to fbgemm if OS is not Linux. This makes sure the behavior is the same on Windows/Mac as the previous default fbgemm qengine on x86 CPUs.
**Test plan**
CI checks.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/93218
Approved by: https://github.com/jgong5, https://github.com/jerryzh168