clipper
clipper copied to clipboard
A low-latency prediction-serving system
The domain containing the docs has expired - when trying to open [clipper.ai](clipper.ai), I get this redirection  Would it be possible to add an offline copy of the docs/potentially...
Bumps commons-io from 2.5 to 2.7. [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a...
To delete, I do the following: ```python def delete_model(name): clipper_conn = ClipperConnection(DockerContainerManager()) clipper_conn.connect() clipper_conn.unlink_model_from_app("sample-app", "sample1") clipper_conn.stop_models(["sample1"]) clipper_conn.unregister_application("sample-app") ``` To register and deploy: ```python clipper_conn.register_application( name="sample-app", input_type="integers", default_output="-1.0", slo_micros=10000000) clipper_conn =...
After passing incorrect input to predict function, I have to scale down and up the model in order to predict again. I think the exceptions from predict function should be...
my env: - OS: win10 - docker: - docker desktop version: 2.4.0 - docker version: 19.03.13 - python: 3.7.7 - clipper-admin: develop I followed this script: ```python from clipper_admin import...
Bumps [junit](https://github.com/junit-team/junit4) from 4.11 to 4.13.1. Release notes Sourced from junit's releases. JUnit 4.13.1 Please refer to the release notes for details. JUnit 4.13 Please refer to the release notes...
Hi, I try to follow the basic query example. After I launch the python script. ` python example_client.py ` I met the following problem. ` 20-10-10:10:49:22 WARNING [decorators.py:34] [default-cluster] Clipper...
recently I tried to bulid Clipper using 0.4 release clone, and I got the error message as below `CMake Error at CMake/folly-deps.cmake:214 (find_package): Could not find a package configuration file...
This PR allows inputs of batch queries (using `input_batch`) to be sent to the model container all together (limited to the maximum batch size), rather than individually. It does this...