ROCm: sgl-kernel enablement starting with sgl_moe_align_block

[HaiShaw]

Motivation

1. Enable sgl-kernel on ROCm, make it easy to add individual kernels
2. Use sgl_moe_align_block kernel for fused_moe for performance

Modifications

As they are.

Checklist

• [+] Format your code according to the Code Formatting with Pre-Commit.
• [+] Add unit tests as outlined in the Running Unit Tests.
• [+] Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• [+] Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.

[HaiShaw]

Pls no review until I fixed docker build ....