serving

From a slack message:

Hi, So I observed that if you deploy a deployment with more replicas than the available resources serve keeps trying to allocate them waiting for autoscaler.

(pid=125021) 2021-09-07 20:52:42,899    INFO http_state.py:75 -- Starting HTTP proxy with name 'pfaUeM:SERVE_CONTROLLER_ACTOR:SERVE_PROXY_ACTOR-node:192.168.1.13-0' on node 'node:192.168.1.13-0' listening on '12

... to make it easier to read Vespa documentation on an e-reader / offline

Vespa documentation is generated using Jekyll from .md and .html files, look into options for generating the artifact as part of site generation (there might be plugins we can use here)

For SC Operator it may be a good idea to generate CRD manifests from inside a docker container.
This should provide reproducible generation step and avoid "produces different output on my machine" issues.

Linter should also fail if generation of manifests produce diff with the commited version.

ReloadableInferEngine::proc_initialize中使用TaskExecutor的是个单例，那么多个模型会一次去设置、启动同一个TaskExecutor；
在调用schedule()之后，TaskExecutor如何确定去调用哪个模型呢？

The format of current master branch UDF output, eva-reuse and my SSD object detector is different. Need a sync format.