docs: update & add new AWS DLCs

[ehcalabres]

Description

This PR adds docs for 2 new AWS DLCs:

• Llama.cpp
• vLLM Omni

Additionaly, it updates the vLLM version to the latest available container

---

Note

Low Risk
Documentation-only changes to DLC URIs and tables; no runtime or application code affected.

Overview
Updates the SageMaker Available DLCs inference page with newer container references and two new serving options.

The vLLM GPU row is bumped from 0.17.0 to 0.21.0, with an updated ECR image (transformers5.8.1, cu130). New sections document vLLM Omni (0.20.0, multimodal on GPU) and Llama.cpp (b9522, separate CPU and GPU images). SGLang, TEI, and Neuron vLLM entries are unchanged.

^{Reviewed by Cursor Bugbot for commit 66c2541. Bugbot is set up for automated code reviews on this repo. Configure here.}

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[pagezyhf]

LGTM!
I think we should also update the FAQ:

• How to choose the right inference container for my use case? can be removed?
• How to find the URI of my container? I'm not sure it's still what we should recommend.
• How to find the URI of my container but simpler? we should migrate to v3.(https://sagemaker.readthedocs.io/en/stable/inference/index.html#migration-from-v2)

[ehcalabres]

Hey @pagezyhf! Yes, maybe I can update the How to find the URI of my container? section with the changes from aws/sagemaker-python-sdk#5960 and we just keep one section for finding the right container URI