docs : clarify tensor split context sizing

[zcxGGmu]

Summary

• clarify that --split-mode tensor shards KV cache and can allow larger context sizes on the same hardware
• note that MTP/speculative decoding should be validated separately when using tensor split
• fix a small spacing typo in the tensor split note

Test Plan

• Documentation-only change; checked with git diff --check

Fixes #25732

Review Complexity : Low

[ggml-gh-bot]

Hi @zcxGGmu, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• PR Template not respected: Please respect the template when creating a new pull request. Make sure to fill out all required sections.

• Multiple open PRs from a new contributor: We limit new contributors (those without a previously merged PR) to 1 open PR at a time. You currently have 2 open PRs.

---

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.