Deepseek sharding for vLLM and MLA kernel plumbing

[khatwanimohit]

Description

• Adds vLLM Ragged Paged Attention (RPA) support for Multi-Latent Attention (MLA) in attention_mla.py using tpu_inference.kernels.mla.v1.kernel.mla_ragged_paged_attention
• Implements mla_rpa_vllm() method for vLLM serving with query absorption and tuned block sizes
• Adds new vllm_deepseek.yml config with expert parallelism sharding rules for DeepSeek models
• Updates deepseek.py layers to pass kv_cache and attention_metadata through attention pipeline
• Modifies KV cache initialization to skip for vllm_rpa attention mode

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

Notice 1: Once all tests pass, the "pull ready" label will automatically be assigned.
This label is used for administrative purposes. Please do not add it manually.

Notice 2: For external contributions, our settings currently require an approval from a MaxText maintainer to trigger CI tests.

Tests

• vllm_decode test using Deepseek3-671B with 4 layers, so I can run it on a v6e-8: https://paste.googleplex.com/6151201055965184
• train_rl command, logs

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 27.94118% with 49 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/maxtext/layers/attention_mla.py	14.00%	41 Missing and 2 partials ⚠️
src/maxtext/layers/moe.py	50.00%	5 Missing ⚠️
src/maxtext/trainers/post_train/rl/train_rl.py	0.00%	1 Missing ⚠️

📢 Thoughts on this report? Let us know!

[NicoGrande]

Can we get rid of this commented line?

[NicoGrande]

Same with this comment.

[github-actions]

This PR has been automatically marked as stale because it has not had recent activity. It will be closed soon if no further activity occurs. Thank you for your contributions.