Peter Pan
Peter Pan
are those all necessary for cobra?
Thank you @barnettZQG , comments addressed
I will merge it if no objection.
Hey, Dear @calind , can you please help ? Or is there any release process which somebody else can offload the work when you are busy?
kind：要预先规划暴露的端口在kind的启动配置kindConfig.yaml 类似 ``` kind: Cluster nodes: - role: control-plane extraPortMappings: - containerPort: 30888 hostPort: 8888 ``` 建议dce5用nodeport方式安装，最后修改svc的nodeport端口，定死为30888（如上例，目前没有固定, 待加强）， `kubectl edit svc istio-ingressgateway -n istio-system` 然后同时要修改keycloak和ghippo的配置, 把kind内网的节点IP改为宿主机的IP，顺便把原来随机分配的noderpot端口改为30888 先helm list -A 查看ghippo的版本，比如是v0.10.0...
per lizhongjun , previous ,in large event database , the sql select which parses json structure is slow. but below sql without unstruct data query is also slow : ```...
is there any workaround so far ? > Thank you for the clearance~~ though I think we could simply adapte the vLLM `vllm.entrypoints.openai.api_server` to the [triton http endpoint](https://github.com/triton-inference-server/server/blob/main/docs/protocol/extension_generate.md#httprest).
any update or progress on this ?
/assign @qiupingdai
 运维者视角有描述了，开发者视角也要补充下 