Skip to main content

llm-d-workload-tuner

This is an experimental Skill. It automatically tunes GKE vLLM inference server parameters and resources based on workload profiles specified in the benchmark configs.

Source facts

Repository
GoogleCloudPlatform/accelerated-platforms
Last source activity
November 3, 2026 at 19:53
Detected SKILL.md language
English
Stars
109
Forks
37

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer
5 files

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
namellm-d-workload-tuner
descriptionThis is an experimental Skill. It automatically tunes GKE vLLM inference server parameters and resources based on workload profiles specified in the benchmark configs.