mirror of
https://github.com/clearml/clearml-docs
synced 2025-02-07 13:21:46 +00:00
Add ClearML Serving 1.0.0 release notes (#324)
This commit is contained in:
parent
c85bfeeb94
commit
48d672f3b8
@ -2,6 +2,28 @@
|
|||||||
title: Version 1.0
|
title: Version 1.0
|
||||||
---
|
---
|
||||||
|
|
||||||
|
### ClearML Serving 1.0.0
|
||||||
|
|
||||||
|
:::warning Backwards Compatibility
|
||||||
|
This release is not backwards compatible
|
||||||
|
:::
|
||||||
|
|
||||||
|
**Breaking Changes**
|
||||||
|
* `preprocess` and `postprocess` class functions get 3 arguments
|
||||||
|
* Add support for per-request state storage, passing information between the pre/post processing functions
|
||||||
|
|
||||||
|
**Features & Bug Fixes**
|
||||||
|
|
||||||
|
* Optimize serving latency while collecting statistics
|
||||||
|
* Fix metric statistics collecting auto-refresh issue
|
||||||
|
* Fix live update of model preprocessing code
|
||||||
|
* Add `pandas` to the default serving container
|
||||||
|
* Add per endpoint/variable statistics collection control
|
||||||
|
* Add `CLEARML_EXTRA_PYTHON_PACKAGES` for easier additional python package support (serving inference container)
|
||||||
|
* Upgrade Nvidia Triton base container image to 22.04 (requires Nvidia drivers 510+)
|
||||||
|
* Add Kubernetes Helm chart
|
||||||
|
|
||||||
|
|
||||||
### ClearML 1.0.5
|
### ClearML 1.0.5
|
||||||
|
|
||||||
**Features**
|
**Features**
|
||||||
|
Loading…
Reference in New Issue
Block a user