Production infrastructure for machine learning at scale
New features
GET
, PUT
, PATCH
, and DELETE
HTTP requests in Realtime APIs (docs) https://github.com/cortexlabs/cortex/pull/2111 https://github.com/cortexlabs/cortex/issues/2063 (RobertLucian)Breaking changes
predict()
has been renamed to handle_post()
in Realtime APIs (handle_get()
, handle_put()
, handle_patch()
, and handle_delete()
are now also supported). For consistency, predict()
has been renamed to handle_async()
for Async APIs, and handle_batch()
for Batch APIs. See the examples for Realtime, Async, and Batch APIs. Task APIs have not been changed.Bug fixes
Docs
Misc
cortex cluster info
command https://github.com/cortexlabs/cortex/pull/2089 https://github.com/cortexlabs/cortex/issues/2062 (RobertLucian)max_instances
== 0 https://github.com/cortexlabs/cortex/pull/2095 (deliahu)New features
Breaking changes
Bug fixes
Misc
cortex cluster configure
command to cortex cluster scale
https://github.com/cortexlabs/cortex/pull/2040 https://github.com/cortexlabs/cortex/issues/1972 (RobertLucian)async_api
to avoid name collision with the reserved keyword in Python 3.7+ https://github.com/cortexlabs/cortex/pull/2066 https://github.com/cortexlabs/cortex/issues/2052 (vishalbollu)cluster up
failures https://github.com/cortexlabs/cortex/pull/2080 https://github.com/cortexlabs/cortex/issues/2027 (vishalbollu)New features
Breaking changes
Bug fixes
Docs
Misc
registryPullQPS
limit from 5 to 10 https://github.com/cortexlabs/cortex/pull/2023 https://github.com/cortexlabs/cortex/issues/1989 (miguelvr)Bug fixes
New features
Breaking changes
on_demand_backup
in cluster configuration has been removed in favour of using a cluster with a mixture of spot and on-demand nodegroups. See multi-instance documentation for aws and gcp for more details.Bug fixes
Docs
Misc
New features
Breaking changes
Bug fixes
Docs
Misc
New features
Breaking changes
requirements.txt
(docs) and/or dependencies.sh
(docs).Bug fixes
Docs
dependencies.sh
(docs) or custom images (docs) https://github.com/cortexlabs/cortex/pull/1862 https://github.com/cortexlabs/cortex/issues/1779 (RobertLucian)Misc
New features
Breaking changes
Bug fixes
downscale_stabilization_period
to be disregarded during downscaling https://github.com/cortexlabs/cortex/pull/1847 https://github.com/cortexlabs/cortex/issues/1846 (RobertLucian)Misc
operator_load_balancer_scheme: internal
in your cluster configuration file, and set up VPC Peering. We plan in supporting a new auth strategy in an upcoming release.New features
TaskAPI
for running arbitrary Python jobs (docs) https://github.com/cortexlabs/cortex/pull/1717 https://github.com/cortexlabs/cortex/issues/253 (miguelvr, RobertLucian)Breaking changes
cortex logs
now streams logs from a single replica at random when there are multiple replicas for an API. The recommended way to analyze production logs is via a dedicated logging tool (by default, logs are sent to CloudWatch on AWS and StackDriver on GCP)Bug fixes
Docs
/mnt
directory for TensorFlow predictors https://github.com/cortexlabs/cortex/pull/1802 https://github.com/cortexlabs/cortex/issues/1792 (deliahu)Misc
New features
Breaking changes
__init__()
and predict()
functions directly. The best way to test your API is to deploy it to a dev/test cluster.predict
CLI command has been deleted. curl
, requests
, etc. are the best tools for testing APIs.Bug fixes
Docs