Update version to 0.32.0

Author: deliahu

build/build-image.sh

@@ -19,7 +19,7 @@ set -euo pipefail
 
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. >/dev/null && pwd)"
 
-CORTEX_VERSION=master
+CORTEX_VERSION=0.32.0
 
 image=$1
 

build/cli.sh

@@ -19,7 +19,7 @@ set -euo pipefail
 
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. >/dev/null && pwd)"
 
-CORTEX_VERSION=master
+CORTEX_VERSION=0.32.0
 
 arg1=${1:-""}
 upload="false"

build/push-image.sh

@@ -17,7 +17,7 @@
 
 set -euo pipefail
 
-CORTEX_VERSION=master
+CORTEX_VERSION=0.32.0
 
 image=$1
 

dev/registry.sh

@@ -14,7 +14,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-CORTEX_VERSION=master
+CORTEX_VERSION=0.32.0
 
 set -eo pipefail
 

docs/clients/install.md

@@ -9,10 +9,10 @@ pip install cortex
 ```
 
 <!-- CORTEX_VERSION_README x2 -->
-To install or upgrade to a specific version (e.g. v0.31.1):
+To install or upgrade to a specific version (e.g. v0.32.0):
 
 ```bash
-pip install cortex==0.31.1
+pip install cortex==0.32.0
 ```
 
 To upgrade to the latest version:
@@ -25,8 +25,8 @@ pip install --upgrade cortex
 
 <!-- CORTEX_VERSION_README x2 -->
 ```bash
-# For example to download CLI version 0.31.1 (Note the "v"):
-bash -c "$(curl -sS https://raw.githubusercontent.com/cortexlabs/cortex/v0.31.1/get-cli.sh)"
+# For example to download CLI version 0.32.0 (Note the "v"):
+bash -c "$(curl -sS https://raw.githubusercontent.com/cortexlabs/cortex/v0.32.0/get-cli.sh)"
 ```
 
 By default, the Cortex CLI is installed at `/usr/local/bin/cortex`. To install the executable elsewhere, export the `CORTEX_INSTALL_PATH` environment variable to your desired location before running the command above.

docs/clients/python.md

@@ -88,7 +88,7 @@ Deploy an API.
 
 **Arguments**:
 
-- `api_spec` - A dictionary defining a single Cortex API. See https://docs.cortex.dev/v/master/ for schema.
+- `api_spec` - A dictionary defining a single Cortex API. See https://docs.cortex.dev/v/0.32/ for schema.
 - `predictor` - A Cortex Predictor class implementation. Not required for TaskAPI/TrafficSplitter kinds.
 - `task` - A callable class/function implementation. Not required for RealtimeAPI/BatchAPI/TrafficSplitter kinds.
 - `requirements` - A list of PyPI dependencies that will be installed before the predictor class implementation is invoked.

docs/clusters/management/create.md

@@ -99,26 +99,26 @@ The docker images used by the cluster can also be overridden. They can be config
 
 <!-- CORTEX_VERSION_BRANCH_STABLE -->
 ```yaml
-image_operator: quay.io/cortexlabs/operator:master
-image_manager: quay.io/cortexlabs/manager:master
-image_downloader: quay.io/cortexlabs/downloader:master
-image_request_monitor: quay.io/cortexlabs/request-monitor:master
-image_cluster_autoscaler: quay.io/cortexlabs/cluster-autoscaler:master
-image_metrics_server: quay.io/cortexlabs/metrics-server:master
-image_inferentia: quay.io/cortexlabs/inferentia:master
-image_neuron_rtd: quay.io/cortexlabs/neuron-rtd:master
-image_nvidia: quay.io/cortexlabs/nvidia:master
-image_fluent_bit: quay.io/cortexlabs/fluent-bit:master
-image_istio_proxy: quay.io/cortexlabs/istio-proxy:master
-image_istio_pilot: quay.io/cortexlabs/istio-pilot:master
-image_prometheus: quay.io/cortexlabs/prometheus:master
-image_prometheus_config_reloader: quay.io/cortexlabs/prometheus-config-reloader:master
-image_prometheus_operator: quay.io/cortexlabs/prometheus-operator:master
-image_prometheus_statsd_exporter: quay.io/cortexlabs/prometheus-statsd-exporter:master
-image_prometheus_dcgm_exporter: quay.io/cortexlabs/prometheus-dcgm-exporter:master
-image_prometheus_kube_state_metrics: quay.io/cortexlabs/prometheus-kube-state-metrics:master
-image_prometheus_node_exporter: quay.io/cortexlabs/prometheus-node-exporter:master
-image_kube_rbac_proxy: quay.io/cortexlabs/kube-rbac-proxy:master
-image_grafana: quay.io/cortexlabs/grafana:master
-image_event_exporter: quay.io/cortexlabs/event-exporter:master
+image_operator: quay.io/cortexlabs/operator:0.32.0
+image_manager: quay.io/cortexlabs/manager:0.32.0
+image_downloader: quay.io/cortexlabs/downloader:0.32.0
+image_request_monitor: quay.io/cortexlabs/request-monitor:0.32.0
+image_cluster_autoscaler: quay.io/cortexlabs/cluster-autoscaler:0.32.0
+image_metrics_server: quay.io/cortexlabs/metrics-server:0.32.0
+image_inferentia: quay.io/cortexlabs/inferentia:0.32.0
+image_neuron_rtd: quay.io/cortexlabs/neuron-rtd:0.32.0
+image_nvidia: quay.io/cortexlabs/nvidia:0.32.0
+image_fluent_bit: quay.io/cortexlabs/fluent-bit:0.32.0
+image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.32.0
+image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.32.0
+image_prometheus: quay.io/cortexlabs/prometheus:0.32.0
+image_prometheus_config_reloader: quay.io/cortexlabs/prometheus-config-reloader:0.32.0
+image_prometheus_operator: quay.io/cortexlabs/prometheus-operator:0.32.0
+image_prometheus_statsd_exporter: quay.io/cortexlabs/prometheus-statsd-exporter:0.32.0
+image_prometheus_dcgm_exporter: quay.io/cortexlabs/prometheus-dcgm-exporter:0.32.0
+image_prometheus_kube_state_metrics: quay.io/cortexlabs/prometheus-kube-state-metrics:0.32.0
+image_prometheus_node_exporter: quay.io/cortexlabs/prometheus-node-exporter:0.32.0
+image_kube_rbac_proxy: quay.io/cortexlabs/kube-rbac-proxy:0.32.0
+image_grafana: quay.io/cortexlabs/grafana:0.32.0
+image_event_exporter: quay.io/cortexlabs/event-exporter:0.32.0
 ```

docs/workloads/async/configuration.md

@@ -26,7 +26,7 @@ predictor:
     shell: <string>  # relative path to a shell script for system package installation (default: dependencies.sh)
   config: <string: value>  # arbitrary dictionary passed to the constructor of the Predictor (optional)
   python_path: <string>  # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
-  image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:master, quay.io/cortexlabs/python-predictor-gpu:master-cuda10.2-cudnn8, or quay.io/cortexlabs/python-predictor-inf:master based on compute)
+  image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.32.0, quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.2-cudnn8, or quay.io/cortexlabs/python-predictor-inf:0.32.0 based on compute)
   env: <string: string>  # dictionary of environment variables
   log_level: <string>  # log level that can be "debug", "info", "warning" or "error" (default: "info")
   shm_size: <string>  # size of shared memory (/dev/shm) for sharing data between multiple processes, e.g. 64Mi or 1Gi (default: Null)
@@ -49,8 +49,8 @@ predictor:
     signature_key:  # name of the signature def to use for prediction (required if your model has more than one signature def)
   config: <string: value>  # arbitrary dictionary passed to the constructor of the Predictor (optional)
   python_path: <string>  # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
-  image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:master)
-  tensorflow_serving_image: <string>  # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-cpu:master, quay.io/cortexlabs/tensorflow-serving-gpu:master, or quay.io/cortexlabs/tensorflow-serving-inf:master based on compute)
+  image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.32.0)
+  tensorflow_serving_image: <string>  # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-cpu:0.32.0, quay.io/cortexlabs/tensorflow-serving-gpu:0.32.0, or quay.io/cortexlabs/tensorflow-serving-inf:0.32.0 based on compute)
   env: <string: string>  # dictionary of environment variables
   log_level: <string>  # log level that can be "debug", "info", "warning" or "error" (default: "info")
   shm_size: <string>  # size of shared memory (/dev/shm) for sharing data between multiple processes, e.g. 64Mi or 1Gi (default: Null)
@@ -72,7 +72,7 @@ predictor:
     path: <string> # S3 path to an exported model directory (e.g. s3://my-bucket/exported_model/) (either this, 'dir', or 'paths' must be provided)
   config: <string: value>  # arbitrary dictionary passed to the constructor of the Predictor (optional)
   python_path: <string>  # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
-  image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-cpu:master or quay.io/cortexlabs/onnx-predictor-gpu:master based on compute)
+  image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-cpu:0.32.0 or quay.io/cortexlabs/onnx-predictor-gpu:0.32.0 based on compute)
   env: <string: string>  # dictionary of environment variables
   log_level: <string>  # log level that can be "debug", "info", "warning" or "error" (default: "info")
   shm_size: <string>  # size of shared memory (/dev/shm) for sharing data between multiple processes, e.g. 64Mi or 1Gi (default: Null)

docs/workloads/async/predictors.md

@@ -132,7 +132,7 @@ class TensorFlowPredictor:
 <!-- CORTEX_VERSION_MINOR -->
 
 Cortex provides a `tensorflow_client` to your Predictor's constructor. `tensorflow_client` is an instance
-of [TensorFlowClient](https://github.com/cortexlabs/cortex/tree/master/pkg/cortex/serve/cortex_internal/lib/client/tensorflow.py)
+of [TensorFlowClient](https://github.com/cortexlabs/cortex/tree/0.32/pkg/cortex/serve/cortex_internal/lib/client/tensorflow.py)
 that manages a connection to a TensorFlow Serving container to make predictions using your model. It should be saved as
 an instance variable in your Predictor, and your `predict()` function should call `tensorflow_client.predict()` to make
 an inference with your exported TensorFlow model. Preprocessing of the JSON payload and postprocessing of predictions
@@ -191,7 +191,7 @@ class ONNXPredictor:
 <!-- CORTEX_VERSION_MINOR -->
 
 Cortex provides an `onnx_client` to your Predictor's constructor. `onnx_client` is an instance
-of [ONNXClient](https://github.com/cortexlabs/cortex/tree/master/pkg/cortex/serve/cortex_internal/lib/client/onnx.py)
+of [ONNXClient](https://github.com/cortexlabs/cortex/tree/0.32/pkg/cortex/serve/cortex_internal/lib/client/onnx.py)
 that manages an ONNX Runtime session to make predictions using your model. It should be saved as an instance variable in
 your Predictor, and your `predict()` function should call `onnx_client.predict()` to make an inference with your
 exported ONNX model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in

docs/workloads/batch/configuration.md

@@ -19,7 +19,7 @@ predictor:
   path: <string>  # path to a python file with a PythonPredictor class definition, relative to the Cortex root (required)
   config: <string: value>  # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
   python_path: <string>  # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
-  image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:master or quay.io/cortexlabs/python-predictor-gpu:master-cuda10.2-cudnn8 based on compute)
+  image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.32.0 or quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.2-cudnn8 based on compute)
   env: <string: string>  # dictionary of environment variables
   log_level: <string>  # log level that can be "debug", "info", "warning" or "error" (default: "info")
   shm_size: <string>  # size of shared memory (/dev/shm) for sharing data between multiple processes, e.g. 64Mi or 1Gi (default: Null)
@@ -49,8 +49,8 @@ predictor:
     batch_interval: <duration>  # the maximum amount of time to spend waiting for additional requests before running inference on the batch of requests
   config: <string: value>  # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
   python_path: <string>  # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
-  image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:master)
-  tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-cpu:master or quay.io/cortexlabs/tensorflow-serving-gpu:master based on compute)
+  image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.32.0)
+  tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-cpu:0.32.0 or quay.io/cortexlabs/tensorflow-serving-gpu:0.32.0 based on compute)
   env: <string: string>  # dictionary of environment variables
   log_level: <string>  # log level that can be "debug", "info", "warning" or "error" (default: "info")
   shm_size: <string>  # size of shared memory (/dev/shm) for sharing data between multiple processes, e.g. 64Mi or 1Gi (default: Null)
@@ -75,7 +75,7 @@ predictor:
       ...
   config: <string: value>  # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
   python_path: <string>  # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
-  image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-cpu:master or quay.io/cortexlabs/onnx-predictor-gpu:master based on compute)
+  image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-cpu:0.32.0 or quay.io/cortexlabs/onnx-predictor-gpu:0.32.0 based on compute)
   env: <string: string>  # dictionary of environment variables
   log_level: <string>  # log level that can be "debug", "info", "warning" or "error" (default: "info")
   shm_size: <string>  # size of shared memory (/dev/shm) for sharing data between multiple processes, e.g. 64Mi or 1Gi (default: Null)

docs/workloads/batch/predictors.md

@@ -143,7 +143,7 @@ class TensorFlowPredictor:
 ```
 
 <!-- CORTEX_VERSION_MINOR -->
-Cortex provides a `tensorflow_client` to your Predictor's constructor. `tensorflow_client` is an instance of [TensorFlowClient](https://github.com/cortexlabs/cortex/tree/master/pkg/cortex/serve/cortex_internal/lib/client/tensorflow.py) that manages a connection to a TensorFlow Serving container to make predictions using your model. It should be saved as an instance variable in your Predictor, and your `predict()` function should call `tensorflow_client.predict()` to make an inference with your exported TensorFlow model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
+Cortex provides a `tensorflow_client` to your Predictor's constructor. `tensorflow_client` is an instance of [TensorFlowClient](https://github.com/cortexlabs/cortex/tree/0.32/pkg/cortex/serve/cortex_internal/lib/client/tensorflow.py) that manages a connection to a TensorFlow Serving container to make predictions using your model. It should be saved as an instance variable in your Predictor, and your `predict()` function should call `tensorflow_client.predict()` to make an inference with your exported TensorFlow model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
 
 When multiple models are defined using the Predictor's `models` field, the `tensorflow_client.predict()` method expects a second argument `model_name` which must hold the name of the model that you want to use for inference (for example: `self.client.predict(payload, "text-generator")`).
 
@@ -204,7 +204,7 @@ class ONNXPredictor:
 ```
 
 <!-- CORTEX_VERSION_MINOR -->
-Cortex provides an `onnx_client` to your Predictor's constructor. `onnx_client` is an instance of [ONNXClient](https://github.com/cortexlabs/cortex/tree/master/pkg/cortex/serve/cortex_internal/lib/client/onnx.py) that manages an ONNX Runtime session to make predictions using your model. It should be saved as an instance variable in your Predictor, and your `predict()` function should call `onnx_client.predict()` to make an inference with your exported ONNX model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
+Cortex provides an `onnx_client` to your Predictor's constructor. `onnx_client` is an instance of [ONNXClient](https://github.com/cortexlabs/cortex/tree/0.32/pkg/cortex/serve/cortex_internal/lib/client/onnx.py) that manages an ONNX Runtime session to make predictions using your model. It should be saved as an instance variable in your Predictor, and your `predict()` function should call `onnx_client.predict()` to make an inference with your exported ONNX model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
 
 When multiple models are defined using the Predictor's `models` field, the `onnx_client.predict()` method expects a second argument `model_name` which must hold the name of the model that you want to use for inference (for example: `self.client.predict(model_input, "text-generator")`).
 

docs/workloads/dependencies/images.md

@@ -11,27 +11,27 @@ mkdir my-api && cd my-api && touch Dockerfile
 Cortex's base Docker images are listed below. Depending on the Cortex Predictor and compute type specified in your API configuration, choose one of these images to use as the base for your Docker image:
 
 <!-- CORTEX_VERSION_BRANCH_STABLE x12 -->
-* Python Predictor (CPU): `quay.io/cortexlabs/python-predictor-cpu:master`
+* Python Predictor (CPU): `quay.io/cortexlabs/python-predictor-cpu:0.32.0`
 * Python Predictor (GPU): choose one of the following:
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda10.0-cudnn7`
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda10.1-cudnn7`
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda10.1-cudnn8`
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda10.2-cudnn7`
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda10.2-cudnn8`
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda11.0-cudnn8`
-  * `quay.io/cortexlabs/python-predictor-gpu:master-cuda11.1-cudnn8`
-* Python Predictor (Inferentia): `quay.io/cortexlabs/python-predictor-inf:master`
-* TensorFlow Predictor (CPU, GPU, Inferentia): `quay.io/cortexlabs/tensorflow-predictor:master`
-* ONNX Predictor (CPU): `quay.io/cortexlabs/onnx-predictor-cpu:master`
-* ONNX Predictor (GPU): `quay.io/cortexlabs/onnx-predictor-gpu:master`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.0-cudnn7`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.1-cudnn7`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.1-cudnn8`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.2-cudnn7`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda10.2-cudnn8`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda11.0-cudnn8`
+  * `quay.io/cortexlabs/python-predictor-gpu:0.32.0-cuda11.1-cudnn8`
+* Python Predictor (Inferentia): `quay.io/cortexlabs/python-predictor-inf:0.32.0`
+* TensorFlow Predictor (CPU, GPU, Inferentia): `quay.io/cortexlabs/tensorflow-predictor:0.32.0`
+* ONNX Predictor (CPU): `quay.io/cortexlabs/onnx-predictor-cpu:0.32.0`
+* ONNX Predictor (GPU): `quay.io/cortexlabs/onnx-predictor-gpu:0.32.0`
 
 The sample `Dockerfile` below inherits from Cortex's Python CPU serving image, and installs 3 packages. `tree` is a system package and `pandas` and `rdkit` are Python packages.
 
 <!-- CORTEX_VERSION_BRANCH_STABLE -->
 ```dockerfile
 # Dockerfile
 
-FROM quay.io/cortexlabs/python-predictor-cpu:master
+FROM quay.io/cortexlabs/python-predictor-cpu:0.32.0
 
 RUN apt-get update \
     && apt-get install -y tree \
@@ -49,7 +49,7 @@ If you need to upgrade the Python Runtime version on your image, you can follow
 ```Dockerfile
 # Dockerfile
 
-FROM quay.io/cortexlabs/python-predictor-cpu:master
+FROM quay.io/cortexlabs/python-predictor-cpu:0.32.0
 
 # upgrade python runtime version
 RUN conda update -n base -c defaults conda