[example] Add support for DBRX

[yanboliang]

Support dbrx from databricks. Initial perf numbers:

|                  |   1 GPU |    2 GPU  | 4 GPU  |    8 GPU   |
|------------------|---------|-----------|--------|------------|
|baseline(bfloat16)|    OOM  |     OOM   | 59.53  |  100.51    |
|        int8      |    OOM  |    66.72  | 91.21  |  146.86    |