Tags → #golang

• 7 Jul 2026

  Building a GPU SaaS Platform - Runtime Ops Boundaries

  Part 22: harden runtime with Secret/TLS config, split RBAC, probes, metrics, and deployment boundaries while keeping audit in the control plane.
• 6 Jul 2026

  Building a GPU SaaS Platform - Reliable Serverless Execution

  Part 21: add queue retry policy, dead-letter handling, execution state classification, and runtime behavior changes for serverless GPU execution.
• 2 Jul 2026

  Building a GPU SaaS Platform - GPU Virtualization with HAMi

  Part 20: add HAMi virtual GPU packages on top of the DRA allocation contract.
• 29 Jun 2026

  Building a GPU SaaS Platform - DRA Package Allocation

  Part 19: replace runtime-side GPU counting with DRA-backed package allocation, ResourceClaim status, and controlled runtime packages.
• 15 Jun 2026

  Building a GPU SaaS Platform - Runtime Control Plane Split

  Part 18: split the runtime into a reconciler-only controller manager and a separate runtime API server.
• 14 Jun 2026

  Building a GPU SaaS Platform - Invocation Result Store

  Part 17: add a ScyllaDB-backed result-store consumer for durable serverless invocation metadata and control-plane result lookup.
• 8 Jun 2026

  Building a GPU SaaS Platform - Worker Lifecycle

  Part 16: add activator-owned worker lifecycle management, prewarm pools, idle scale-down, and metrics-driven worker state.
• 31 May 2026

  Building a GPU SaaS Platform - Worker Sidecar

  Part 15: add a serverless worker sidecar, define a UDS framework contract, and return results and metrics through NATS.
• 17 May 2026

  Building a GPU SaaS Platform - Activator Dispatch

  Part 14: add a dedicated activator that consumes ingress invocations, selects or creates GPUUnit workers, and publishes worker-targeted dispatch messages.
• 10 May 2026

  Building a GPU SaaS Platform - Queue-First Ingress

  Part 13: record the runtime-side serverless contract on GPU units and enqueue invocations durably through NATS JetStream before any worker executes them.