open-inference-protocol
open-inference-protocol copied to clipboard
kserve
Repository for open inference protocol specification
The current specification does not allow for good use of _Cache Control_ i.e., client side caching, which is inefficient in production environments. The specification should add a GET request for...
I would like to help with this protocol specification, I've watched the first zoom recording, and read through the notes, but my next question is, when does the WG meet...
Proto file accepts `//` for single line comment and `/* */` for multi-line commenting and does not accept `#` as a valid single line comment. This `#` style commenting throws...
Curiously, the OpenAPI REST specification documents that the server may return HTTP status code 400 in some situations, but not in others that seemingly would have a higher propensity for...
Generating a client based on the OpenAPI REST specification yields some pretty unusable clients, something that can go a long way is coming up with some half decent `operationId` The...
The path parameters described in the OpenAPI REST document do not seem to follow the spec on how path parameters are described: https://spec.openapis.org/oas/v3.1.0#path-templating. Is this intentional? Does some build tooling...
The descriptions for "_Model Ready_" and "_Model Metadata_" in both the REST and gRPC specifications claim that the model version is optional. Is this true? If so, the specification should...
With the increasing popularity of LLMs, many companies have started to look into deploying LLMs. Instead of `infer/predict`, `completions` and `embeddings` are being used. Most of the API supports `stream`....
Clarification about encoding of BYTES data in JSON might be useful. For example, TFServing specifies that binary data be encoded using base64: https://www.tensorflow.org/tfx/serving/api_rest#encoding_binary_values
The existing links to OIP adoptions in Seldon Core and OpenVINO (REST and gRPC APIs) were outdated. This change updates them to their current working locations.
