You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Oct 15, 2025. It is now read-only.
Request completely sent off
< HTTP/1.1 500 Internal Server Error
< date: Fri, 18 Jul 2025 10:14:38 GMT
< server: istio-envoy
< content-length: 0
<
Connection #0 to host localhost left intact
Steps to reproduce
1 run llmd-installer.sh,
2 test GET /v1/models via the gateway ,but i do it in this way
2.1 in k8s master node(btw my cluster is only one node), "kubectl port-forward -n llm-d service/llm-d-inference-gateway-istio 8081:80"
2.2 "curl -v http://localhost:8081/v1/models"
Component
Other
Describe the bug
/llm-d-deployer/quickstart# curl -v http://localhost:8081/v1/models \
< HTTP/1.1 500 Internal Server Error
< date: Fri, 18 Jul 2025 10:14:38 GMT
< server: istio-envoy
< content-length: 0
<
Steps to reproduce
1 run llmd-installer.sh,
2 test GET /v1/models via the gateway ,but i do it in this way
2.1 in k8s master node(btw my cluster is only one node), "kubectl port-forward -n llm-d service/llm-d-inference-gateway-istio 8081:80"
2.2 "curl -v http://localhost:8081/v1/models"
Additional context or screenshots
No response