---
title: "Livez"
method: GET
path: "/livez"
tags: ["health"]
---

# Livez

`GET /livez`

GPU-aware liveness probe.

Unlike /healthz (process-alive only), this exercises the GPU with a tiny CUDA
sync. A wedged CUDA context (``device-side assert``) is unrecoverable in
PyTorch, so failing liveness lets the kubelet restart the pod — the only path
back to a serving worker.

It deliberately does NOT consult the lifecycle ready flag, so graceful
shutdown draining (when the worker marks itself not-ready) never trips a
restart. Wire this to the K8s ``livenessProbe`` with a tolerant
``failureThreshold`` so a momentarily busy GPU is not mistaken for a wedge.

Returns:
    200 OK with "ok" body if the GPU can run a kernel (or this is a CPU
    worker). 503 Service Unavailable with "gpu unhealthy" if wedged.

## Response `200`

Successful Response

- unknown

---

[API](https://skmtc.dev/superlinked/apis/sie-server.md) · [All operations](https://skmtc.dev/superlinked/apis/sie-server/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/superlinked/sie-server/revisions/26ac644915a4/schema)