GoogleCloudPlatform/accelerated-platforms

llm-d-benchmarking

Benchmarks a deployed llm-d well-lit path guide stack on GKE using llm-d-benchmark cli with inference-perf as the harness, the user a will select the appropriate workload profiles from llm-d-benchmark.

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.

gke-inference-stack-deploy

Deploys the GKE base platform and inference-specific terra-services (GPU/TPU) for accelerated workloads.

llm-d-deploy-stack

Deploys the llm-d stack on GKE using well-lit paths specification.