serving

Search before asking

• I searched the issues and found no similar issues.

Ray Component

Ray Clusters

What happened + What you expected to happen

I was trying to launch a Ray cluster on GCP via my macOS. When I disabled the docker field and used the setup_commands field to set up the new node, everything went well. However, when

... 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)

The documentation for creating complex inference graphs should include what components can be connected to what, and how the overall graph should behave.

For example, all inference graphs need to end with a single node, whether its a combiner combining multiple inputs, or a transformer, or a model--the graph can't split and then never rejoin, etc.

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？

Currently in DingoDB, there is only one schema named 'DINGO', which is statically bound to a single meta service.

If there are serveral meta services provided, some other schema names are needed.

A "schema name --- meta service provider" register mechanism is good for maximize flexibility.

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