serving icon indicating copy to clipboard operation
serving copied to clipboard

A flexible, high-performance serving system for machine learning models

Results 219 serving issues
Sort by recently updated
recently updated
newest added

This PR adds a workflow that runs C++ tests using Bazel to run gtest. There are currently build failures in some of the proto modules that prevent the tests from...

### PR Description: This PR introduces a check to detect potential typos in the monitoring config file name by calculating the **Levenshtein distance** between the provided file name and the...

I am trying to use tensorflow serving to serve a keras bert model, but I have problem to predict with rest api, below are informations. Can you please help me...

stat:awaiting tensorflower
type:bug

Hi, I'm trying to cross-compile TensorFlow Serving on an x86_64 host for Jetson Nano (aarch64 target) without using Docker or any container. However, the process with Bazel (hermetic 💩) has...

type:support

The latest version contains following vulnerabilites, +------------------+----------+------+---------+---------+-------------------------------------+-----------+------------+----------------------------------------------------+ | CVE | SEVERITY | CVSS | PACKAGE | VERSION | STATUS | PUBLISHED | DISCOVERED | DESCRIPTION | +------------------+----------+------+---------+---------+-------------------------------------+-----------+------------+----------------------------------------------------+ | CVE-2019-12900 |...

Based on the rest of the documentation and looking at the code, it appears that this should be `NaN` and that `Nan` is invalid. This also matches what the Python...

----------------------- ## 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 There is...

type:feature
stat:awaiting tensorflower

In TensorFlow _version 2.16_ (and later), the convolution operation implementation for _FP32_ data type in oneDNN was changed from **gemm:acl** to **gemm:ref**. However, this change has resulted in performance degradation...

type:performance

maybe related: tensorflow/serving#2267 This pull request updates the embedded TensorFlow Text from version 2.12.1 to 2.18.1. Currently, TensorFlow Serving container images cannot load models trained using TensorFlow Text 2.16.1 or...

The build argument TF_SERVING_VERSION_GIT_BRANCH was ignored in both dockerfiles, although it was correctly handled in .devel-mkl. I just copied&pasted the same "git clone" lines from mkl. Now the command `docker...