[DP] Functional DP for GPT-OSS

[wenxindongwork]

Description

Add functional DP support for GPT-OSS Torchax backend.

Verified baseline throughput unchanged (5037.82) , DP=2 throughput is 1.54x (7781.92).

Validated numerical correctness with offline_inference.py

Full details: https://paste.googleplex.com/5240826907197440

Tests

https://buildkite.com/tpu-commons/tpu-inference-ci/builds/5712
https://buildkite.com/tpu-commons/tpu-inference-ci/builds/5851

Checklist

Before submitting this PR, please make sure:

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have made or will make corresponding changes to any relevant documentation.

[github-actions]

Description

Start with a short description of what the PR does and how this is a change from
the past.

The rest of the description includes relevant details and context, examples:

• why is this change being made,
• the problem being solved and any relevant context,
• why this is a good solution,
• some information about the specific implementation,
• shortcomings of the solution and possible future improvements.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Tests

Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

Before submitting this PR, please make sure:

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have made or will make corresponding changes to any relevant documentation.

[kyuyeunk]

Please add torchax dp related unit tests.

[kyuyeunk]

Please add torchax dp related unit tests.

Also, please address this comment.

[wenxindongwork]

added e2e model parallelism test for Llama3.1 1b for torchax.