[Doc]: Improve feature tables

[hmellor]

• Use ❌ and ❔ instead of ASCII characters
• Replace some ❌ with ✅ if features are now supported/compatible
• Add vertical-table-header CSS class to make "Feature x Feature" table more readable:
  

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[DarkLight1337]

cc @mgoin @robertgshaw2-redhat to confirm the updates to other feature compatibilities.

[DarkLight1337]

Perhaps we should use a different symbol for partial support?

[hmellor]

Sure, that sounds like a good idea

[DarkLight1337]

Can you also use this for multi-modal + prefix caching?

[DarkLight1337]

The multimodal part LGTM

[mgoin]

Awesome, the quantization table looks good to me. FYI we had to use the crappy ascii check and cross before because of RST support issues. Now that we are in markdown, I'm glad we can use nice looking emojis :)