Update version to 0.26.0

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=0.26.0
 
 image=$1
 dir="${ROOT}/images/${image/-slim}"

build/cli.sh

@@ -19,7 +19,7 @@ set -euo pipefail
 
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. >/dev/null && pwd)"
 
-CORTEX_VERSION=master
+CORTEX_VERSION=0.26.0
 
 arg1=${1:-""}
 upload="false"

build/push-image.sh

@@ -17,7 +17,7 @@
 
 set -euo pipefail
 
-CORTEX_VERSION=master
+CORTEX_VERSION=0.26.0
 
 image=$1
 

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. v0.25.0):
+To install or upgrade to a specific version (e.g. v0.26.0):
 
 ```bash
-pip install cortex==0.25.0
+pip install cortex==0.26.0
 ```
 
 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 0.25.0 (Note the "v"):
-$ bash -c "$(curl -sS https://raw.githubusercontent.com/cortexlabs/cortex/v0.25.0/get-cli.sh)"
+# For example to download CLI version 0.26.0 (Note the "v"):
+$ bash -c "$(curl -sS https://raw.githubusercontent.com/cortexlabs/cortex/v0.26.0/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

@@ -91,7 +91,7 @@ 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/0.26/ for schema.
 - `predictor` - A Cortex Predictor class implementation. Not required when deploying a traffic splitter.
 - `requirements` - A list of PyPI dependencies that will be installed before the predictor class implementation is invoked.
 - `conda_packages` - A list of Conda dependencies that will be installed before the predictor class implementation is invoked.

docs/clusters/aws/install.md

@@ -89,17 +89,17 @@ The docker images used by the Cortex cluster can also be overridden, although th
 
 <!-- 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_fluentd: quay.io/cortexlabs/fluentd:master
-image_statsd: quay.io/cortexlabs/statsd:master
-image_istio_proxy: quay.io/cortexlabs/istio-proxy:master
-image_istio_pilot: quay.io/cortexlabs/istio-pilot:master
+image_operator: quay.io/cortexlabs/operator:0.26.0
+image_manager: quay.io/cortexlabs/manager:0.26.0
+image_downloader: quay.io/cortexlabs/downloader:0.26.0
+image_request_monitor: quay.io/cortexlabs/request-monitor:0.26.0
+image_cluster_autoscaler: quay.io/cortexlabs/cluster-autoscaler:0.26.0
+image_metrics_server: quay.io/cortexlabs/metrics-server:0.26.0
+image_inferentia: quay.io/cortexlabs/inferentia:0.26.0
+image_neuron_rtd: quay.io/cortexlabs/neuron-rtd:0.26.0
+image_nvidia: quay.io/cortexlabs/nvidia:0.26.0
+image_fluentd: quay.io/cortexlabs/fluentd:0.26.0
+image_statsd: quay.io/cortexlabs/statsd:0.26.0
+image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.26.0
+image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.26.0
 ```

docs/clusters/gcp/install.md

@@ -51,11 +51,11 @@ The docker images used by the Cortex cluster can also be overridden, although th
 
 <!-- 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_statsd: quay.io/cortexlabs/statsd:master
-image_istio_proxy: quay.io/cortexlabs/istio-proxy:master
-image_istio_pilot: quay.io/cortexlabs/istio-pilot:master
-image_pause: quay.io/cortexlabs/pause:master
+image_operator: quay.io/cortexlabs/operator:0.26.0
+image_manager: quay.io/cortexlabs/manager:0.26.0
+image_downloader: quay.io/cortexlabs/downloader:0.26.0
+image_statsd: quay.io/cortexlabs/statsd:0.26.0
+image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.26.0
+image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.26.0
+image_pause: quay.io/cortexlabs/pause:0.26.0
 ```

docs/workloads/batch/configuration.md

@@ -11,7 +11,7 @@
     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 based on compute)
+    image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.26.0 or quay.io/cortexlabs/python-predictor-gpu:0.26.0 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)
@@ -46,8 +46,8 @@
       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-gpu:master or quay.io/cortexlabs/tensorflow-serving-cpu:master based on compute)
+    image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.26.0)
+    tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu:0.26.0 or quay.io/cortexlabs/tensorflow-serving-cpu:0.26.0 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)
@@ -77,7 +77,7 @@
         ...
     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-gpu:master or quay.io/cortexlabs/onnx-predictor-cpu:master based on compute)
+    image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu:0.26.0 or quay.io/cortexlabs/onnx-predictor-cpu:0.26.0 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/0.26/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")`).
 
@@ -202,6 +202,6 @@ 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/0.26/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

@@ -11,19 +11,19 @@ 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-slim:master`
+* Python Predictor (CPU): `quay.io/cortexlabs/python-predictor-cpu-slim:0.26.0`
 * Python Predictor (GPU): choose one of the following:
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda10.0-cudnn7`
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda10.1-cudnn7`
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda10.1-cudnn8`
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda10.2-cudnn7`
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda10.2-cudnn8`
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda11.0-cudnn8`
-  * `quay.io/cortexlabs/python-predictor-gpu-slim:master-cuda11.1-cudnn8`
-* Python Predictor (Inferentia): `quay.io/cortexlabs/python-predictor-inf-slim:master`
-* TensorFlow Predictor (CPU, GPU, Inferentia): `quay.io/cortexlabs/tensorflow-predictor-slim:master`
-* ONNX Predictor (CPU): `quay.io/cortexlabs/onnx-predictor-cpu-slim:master`
-* ONNX Predictor (GPU): `quay.io/cortexlabs/onnx-predictor-gpu-slim:master`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda10.0-cudnn7`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda10.1-cudnn7`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda10.1-cudnn8`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda10.2-cudnn7`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda10.2-cudnn8`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda11.0-cudnn8`
+  * `quay.io/cortexlabs/python-predictor-gpu-slim:0.26.0-cuda11.1-cudnn8`
+* Python Predictor (Inferentia): `quay.io/cortexlabs/python-predictor-inf-slim:0.26.0`
+* TensorFlow Predictor (CPU, GPU, Inferentia): `quay.io/cortexlabs/tensorflow-predictor-slim:0.26.0`
+* ONNX Predictor (CPU): `quay.io/cortexlabs/onnx-predictor-cpu-slim:0.26.0`
+* ONNX Predictor (GPU): `quay.io/cortexlabs/onnx-predictor-gpu-slim:0.26.0`
 
 Note: the images listed above use the `-slim` suffix; Cortex's default API images are not `-slim`, since they have additional dependencies installed to cover common use cases. If you are building your own Docker image, starting with a `-slim` Predictor image will result in a smaller image size.
 
@@ -33,7 +33,7 @@ The sample `Dockerfile` below inherits from Cortex's Python CPU serving image, a
 ```dockerfile
 # Dockerfile
 
-FROM quay.io/cortexlabs/python-predictor-cpu-slim:master
+FROM quay.io/cortexlabs/python-predictor-cpu-slim:0.26.0
 
 RUN apt-get update \
     && apt-get install -y tree \

docs/workloads/realtime/configuration.md

@@ -25,7 +25,7 @@
     threads_per_process: <int>  # the number of threads per process (default: 1)
     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 or quay.io/cortexlabs/python-predictor-gpu:master based on compute)
+    image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.26.0 or quay.io/cortexlabs/python-predictor-gpu:0.26.0 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)
@@ -81,8 +81,8 @@
     threads_per_process: <int>  # the number of threads per process (default: 1)
     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-gpu:master or quay.io/cortexlabs/tensorflow-serving-cpu:master based on compute)
+    image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.26.0)
+    tensorflow_serving_image: <string>  # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu:0.26.0 or quay.io/cortexlabs/tensorflow-serving-cpu:0.26.0 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)
@@ -133,7 +133,7 @@
     threads_per_process: <int>  # the number of threads per process (default: 1)
     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-gpu:master or quay.io/cortexlabs/onnx-predictor-cpu:master based on compute)
+    image: <string>  # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu:0.26.0 or quay.io/cortexlabs/onnx-predictor-cpu:0.26.0 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)