Fix dummy weight support in vLLM decode.

[NicoGrande]

Description

This PR fixes support for running vLLM decode with dummy weights. This was previously failing when load_parameters_config=None as Pydantic expects a string with "" being the default.

Additionally this PR adds the logical axis rules context manager necessary to shard the model upon initialization.

Tests

Running vLLM decode with dummy weights.

Checklist

Before submitting this PR, please make sure (put X in square brackets):

• I have performed a self-review of my code. For an optional AI review, add the gemini-review label.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have run end-to-end tests tests and provided workload links above if applicable.
• I have made or will make corresponding changes to the doc if needed, including adding new documentation pages to the relevant Table of Contents (toctree directive) as explained in our documentation.

[codecov]

Codecov Report

❌ Patch coverage is 0% with 10 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/MaxText/vllm_decode.py	0.00%	10 Missing ⚠️

📢 Thoughts on this report? Let us know!

[richjames0]

lgtm