# Kubernetes LLM Platform

## Docs

- [Architecture](https://ai.wmx.dev/architecture/index.md)
- [Cold start](https://ai.wmx.dev/architecture/lessons/cold-start.md)
- [GPU signals](https://ai.wmx.dev/architecture/lessons/gpu-signals-and-autoscaling.md)
- [Concepts](https://ai.wmx.dev/architecture/lessons/index.md)
- [Operational gotchas](https://ai.wmx.dev/architecture/lessons/operational-gotchas.md)
- [Portability](https://ai.wmx.dev/architecture/lessons/portability.md)
- [Serving layers compared](https://ai.wmx.dev/architecture/serving-layers.md)
- [Benchmark results](https://ai.wmx.dev/benchmarks.md)
- [Design rationale](https://ai.wmx.dev/decisions/index.md)
- [1. Configure](https://ai.wmx.dev/getting-started/configure.md)
- [Get started](https://ai.wmx.dev/getting-started/index.md)
- [3. Install the platform](https://ai.wmx.dev/getting-started/install-platform.md)
- [2. Provision infrastructure](https://ai.wmx.dev/getting-started/provision-infra.md)
- [Benchmarking](https://ai.wmx.dev/guides/benchmarking.md)
- [Change models](https://ai.wmx.dev/guides/change-or-add-a-model.md)
- [Coding assistant](https://ai.wmx.dev/guides/coder-stack.md)
- [GPU debugging](https://ai.wmx.dev/guides/gpu-debugging.md)
- [Guardrails](https://ai.wmx.dev/guides/guardrails.md)
- [Guides](https://ai.wmx.dev/guides/index.md)
- [Inference gateway](https://ai.wmx.dev/guides/inference-gateway.md)
- [KEDA autoscaling](https://ai.wmx.dev/guides/keda-autoscaling.md)
- [API key portal](https://ai.wmx.dev/guides/key-portal.md)
- [KServe](https://ai.wmx.dev/guides/kserve.md)
- [OCI modelcar](https://ai.wmx.dev/guides/kserve-modelcar.md)
- [LiteLLM tenant gateway](https://ai.wmx.dev/guides/litellm.md)
- [Spend dashboard](https://ai.wmx.dev/guides/litellm-spend-dashboard.md)
- [n8n automation](https://ai.wmx.dev/guides/n8n.md)
- [Pending GPU workloads](https://ai.wmx.dev/guides/pending-gpu-workloads.md)
- [Production HA](https://ai.wmx.dev/guides/prod-ha-validation.md)
- [Secret contract](https://ai.wmx.dev/guides/secret-contract.md)
- [Security enforcement](https://ai.wmx.dev/guides/security-enforcement.md)
- [SSO with Dex](https://ai.wmx.dev/guides/sso-dex.md)
- [Staged bring-up](https://ai.wmx.dev/guides/staged-bring-up.md)
- [Switch serving layer](https://ai.wmx.dev/guides/switch-serving-layer.md)
- [Validation and teardown](https://ai.wmx.dev/guides/teardown.md)
- [Raw vLLM](https://ai.wmx.dev/guides/vllm-serving.md)
- [Kubernetes LLM Platform](https://ai.wmx.dev/index.md)
- [agentgateway egress and MCP](https://ai.wmx.dev/reference/agentgateway.md)
- [Glossary](https://ai.wmx.dev/reference/glossary.md)
- [Reference](https://ai.wmx.dev/reference/index.md)
- [Make targets](https://ai.wmx.dev/reference/make-targets.md)
- [Model catalog](https://ai.wmx.dev/reference/model-catalog.md)
- [Repo layout](https://ai.wmx.dev/reference/repo-layout.md)
- [Future Roadmap](https://ai.wmx.dev/reference/roadmap.md)
- [Secrets](https://ai.wmx.dev/reference/secrets.md)
- [Security posture](https://ai.wmx.dev/reference/security.md)
- [Trust model](https://ai.wmx.dev/reference/trust-model.md)