cld2labs/Qwen3-8b

[arpannookala-12]

Summary

• Adds model card for Qwen3-8B (Alibaba Cloud / Qwen Team) under third_party/Dell/model-deployment/Qwen3-8b/
• Adds Helm-based deployment guide for deploying Qwen3-8B via vLLM on CPU (Xeon) with Keycloak OIDC and APISIX ingress

[alexsin368]

Model deployed successfully. Getting Gateway Time-out error when testing inference.

vLLM pod has no issues. Ingress-nginx-controller saying upstream timed out:

2026/05/18 22:53:31 [error] 153281#153281: *6540963 upstream timed out (110: Operation timed out) while reading response header from upstream, client: 172.17.23.1, server: api.example.com, request: "POST /Qwen3-8B-vllmcpu/v1/completions HTTP/2.0", upstream: "http://10.233.104.80:9080/Qwen3-8B-vllmcpu/v1/completions", host: "api.example.com"
172.17.23.1 - - [18/May/2026:22:53:31 +0000] "POST /Qwen3-8B-vllmcpu/v1/completions HTTP/2.0" 504 160 "-" "curl/7.81.0" 1204 60.001 [auth-apisix-auth-apisix-gateway-80] [] 10.233.104.80:9080 0 60.001 504 b2fca060a21ad0bc39ba893529293cbd