serving

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

the ci/travis folder is confusing. The ci/README.md also mentions Travis, could be interpreted in all sorts of ways. maybe time to change that to something more agnostic? After all, we're not using Travis anymore.

Use case

... 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.

https://github.com/pytorch/serve/blob/6a191f822f2e759c2aad07b8f9eacbedcb039827/model-archiver/model_archiver/model_packaging_utils.py#L137

In a multi-user system, this line can raise Permission Error because of the same file name in the shared /tmp/ directory which maybe created by another user. Maybe we can give more unique name when we store it using timestamp or something.

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.