serving
serving copied to clipboard
A flexible, high-performance serving system for machine learning models
updated `Dockerfile.gpu` to install `cuda-toolkit` to avoid error "error: libdevice not found at ./libdevice.10.bc". Ref: #2201
## Bug Report If this is a bug report, please fill out the following form in full: ### System information - **OS Platform and Distribution : macOS Bigsur 11.4 -...
## Feature Request ### Describe the problem the feature is intended to solve The gRPC server for tensorflow/serving does not currently support gRPC server reflection. This makes it difficult to...
## Feature Request Please release version 2.15 ### Describe the problem the feature is intended to solve We want to upgrade to tensorflow version 2.15 but are blocked by a...
Proposed changes are an extension for https://github.com/tensorflow/tensorflow/pull/60190. These changes enable string tensors in TFLite models which were generated on LE machines to be loaded successfully on BE platforms. Below test...
Updated some references to ancient, deprecated methods (apt-key, apt-get)
Changes in this PR: 1) Add file constant.js for script level constant values. 2) Add file CSAT.yml to invoke the workflow and call the script when closed event occur. 3)...
I built and installed the whl package for serving on ROCM myself, but found that only the pip list method was used to view the version of serving, while the...
[PluggableDevice](https://github.com/tensorflow/community/blob/master/rfcs/20200624-pluggable-device-for-tensorflow.md) architecture offers a plugin mechanism for registering devices with TensorFlow without the need to make changes in TensorFlow code. It relies on C APIs to communicate with the TensorFlow...
## Feature Request If this is a feature request, please fill out the following form in full: ### Describe the problem the feature is intended to solve According to my...