[TASK] Seperate AutoTP workflow

As discussed in this PR (https://github.com/microsoft/DeepSpeed/pull/4721), we need to increase test coverage for AutoTP to cover more models. Such workflow can help avoid regressions such as https://github.com/microsoft/DeepSpeed/issues/4774

This is a challenge in current UT scope because of the following points:

1. Popular models has very large model checkpoints (~6B to ~180B), we need an instance large enough to be able to download and run these large models.
2. To test effectiveness of AutoTP, certain metric i.e. accuracy or perplexity will be needed to verify the effectiveness of AutoTP
3. The workflow needs to be expandable to new model supported by DeepSpeed.

The workflow may also run the following variants:

1. load checkpoint with from_config as memory efficient form.
2. Quantization form of the model.
3. 3 devices to test uneven sharding.

The expected result of this task is:

1. A workflow that can regularly test the AutoTP status of each model and post test result. (pass/fail, accuracy, etc.) This can complement the manually maintained list (https://github.com/microsoft/DeepSpeed/blob/master/docs/_tutorials/automatic-tensor-parallelism.md) which is often out of sync.
2. A test script that people can use to reproduce and report AutoTP related issues.
3. Better integration process of new model AutoTP support (what was broken, which PR fixed it, etc.)