Tag: vllm

1 entry tagged "vllm" — 1 post, 0 links.

Posts

Jul 16, 20269 min — Platform & AI

A Private GPT-OSS Service on Cloud Run

A production-oriented Cloud Run and vLLM design that keeps GPT-OSS private, separates routing from inference, and makes model loading, readiness, concurrency, and rollback explicit.

Outcome: Produced a deployable service contract for private OpenAI-compatible inference with IAM authentication, pinned artifacts, measured concurrency, and a scale-to-zero operating path.

All tags