feat: add gguff plugin to vllm runtime

[axsapronov]

Hi folks.
vllm can run gguf models, but... since 0.24.0 vllm moved this logic to plugin. This PR installs this plugin.

[gemini-code-assist]

Code Review

This pull request adds the installation of the vllm-gguf-plugin across multiple vLLM Dockerfiles (CANN, CUDA, DTK, HGGC, MACA, and ROCm). However, several of these Dockerfiles (DTK, HGGC, and MACA) are pinned to older vLLM versions (0.18.1, 0.18.0, and 0.21.0, respectively) where GGUF support is already built-in. Installing the external plugin on these older versions is unnecessary and will cause dependency resolution failures or unintended upgrades. It is recommended to revert the GGUF plugin installation changes for the DTK, HGGC, and MACA Dockerfiles.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.