You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/deployments/batch-api/api-configuration.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,7 +16,7 @@ Reference the section below which corresponds to your Predictor type: [Python](#
16
16
path: <string> # path to a python file with a PythonPredictor class definition, relative to the Cortex root (required)
17
17
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
18
18
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
19
-
image: <string> # docker image to use for the Predictor (default: cortexlabs/python-predictor-cpu or cortexlabs/python-predictor-gpu based on compute)
19
+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu or quay.io/cortexlabs/python-predictor-gpu based on compute)
20
20
env: <string: string> # dictionary of environment variables
21
21
networking:
22
22
endpoint: <string> # the endpoint for the API (default: <api_name>)
@@ -50,8 +50,8 @@ See additional documentation for [compute](../compute.md), [networking](../netwo
50
50
batch_interval: <duration> # the maximum amount of time to spend waiting for additional requests before running inference on the batch of requests
51
51
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
52
52
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
53
-
image: <string> # docker image to use for the Predictor (default: cortexlabs/tensorflow-predictor)
54
-
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: cortexlabs/tensorflow-serving-gpu or cortexlabs/tensorflow-serving-cpu based on compute)
53
+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor)
54
+
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu or quay.io/cortexlabs/tensorflow-serving-cpu based on compute)
55
55
env: <string: string> # dictionary of environment variables
56
56
networking:
57
57
endpoint: <string> # the endpoint for the API (default: <api_name>)
@@ -81,7 +81,7 @@ See additional documentation for [compute](../compute.md), [networking](../netwo
81
81
...
82
82
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
83
83
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
84
-
image: <string> # docker image to use for the Predictor (default: cortexlabs/onnx-predictor-gpu or cortexlabs/onnx-predictor-cpu based on compute)
84
+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu or quay.io/cortexlabs/onnx-predictor-cpu based on compute)
85
85
env: <string: string> # dictionary of environment variables
86
86
networking:
87
87
endpoint: <string> # the endpoint for the API (default: <api_name>)
Copy file name to clipboardExpand all lines: docs/deployments/realtime-api/api-configuration.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,7 +27,7 @@ Reference the section below which corresponds to your Predictor type: [Python](#
27
27
threads_per_process: <int> # the number of threads per process (default: 1)
28
28
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (optional)
29
29
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
30
-
image: <string> # docker image to use for the Predictor (default: cortexlabs/python-predictor-cpu or cortexlabs/python-predictor-gpu based on compute)
30
+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu or quay.io/cortexlabs/python-predictor-gpu based on compute)
31
31
env: <string: string> # dictionary of environment variables
32
32
networking:
33
33
endpoint: <string> # the endpoint for the API (aws only) (default: <api_name>)
@@ -88,8 +88,8 @@ See additional documentation for [models](models.md), [parallelism](parallelism.
88
88
threads_per_process: <int> # the number of threads per process (default: 1)
89
89
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (optional)
90
90
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
91
-
image: <string> # docker image to use for the Predictor (default: cortexlabs/tensorflow-predictor)
92
-
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: cortexlabs/tensorflow-serving-gpu or cortexlabs/tensorflow-serving-cpu based on compute)
91
+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor)
92
+
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu or quay.io/cortexlabs/tensorflow-serving-cpu based on compute)
93
93
env: <string: string> # dictionary of environment variables
94
94
networking:
95
95
endpoint: <string> # the endpoint for the API (aws only) (default: <api_name>)
@@ -145,7 +145,7 @@ See additional documentation for [models](models.md), [parallelism](parallelism.
145
145
threads_per_process: <int> # the number of threads per process (default: 1)
146
146
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (optional)
147
147
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
148
-
image: <string> # docker image to use for the Predictor (default: cortexlabs/onnx-predictor-gpu or cortexlabs/onnx-predictor-cpu based on compute)
148
+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu or quay.io/cortexlabs/onnx-predictor-cpu based on compute)
149
149
env: <string: string> # dictionary of environment variables
150
150
networking:
151
151
endpoint: <string> # the endpoint for the API (aws only) (default: <api_name>)
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:
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.
67
67
@@ -71,7 +71,7 @@ The sample Dockerfile below inherits from Cortex's Python CPU serving image, and
@@ -132,7 +132,7 @@ Update your API configuration file to point to your image:
132
132
...
133
133
```
134
134
135
-
*Note: for [TensorFlow Predictors](#tensorflow-predictor), two containers run together to serve predictions: one runs your Predictor code (`cortexlabs/tensorflow-predictor`), and the other is TensorFlow serving to load the SavedModel (`cortexlabs/tensorflow-serving-gpu` or `cortexlabs/tensorflow-serving-cpu`). There's a second available field `tensorflow_serving_image` that can be used to override the TensorFlow Serving image. Both of the default serving images (`cortexlabs/tensorflow-serving-gpu` and `cortexlabs/tensorflow-serving-cpu`) are based on the official TensorFlow Serving image (`tensorflow/serving`). Unless a different version of TensorFlow Serving is required, the TensorFlow Serving image shouldn't have to be overridden, since it's only used to load the SavedModel and does not run your Predictor code.*
135
+
*Note: for [TensorFlow Predictors](#tensorflow-predictor), two containers run together to serve predictions: one runs your Predictor code (`quay.io/cortexlabs/tensorflow-predictor`), and the other is TensorFlow serving to load the SavedModel (`quay.io/cortexlabs/tensorflow-serving-gpu` or `quay.io/cortexlabs/tensorflow-serving-cpu`). There's a second available field `tensorflow_serving_image` that can be used to override the TensorFlow Serving image. Both of the default serving images (`quay.io/cortexlabs/tensorflow-serving-gpu` and `quay.io/cortexlabs/tensorflow-serving-cpu`) are based on the official TensorFlow Serving image (`tensorflow/serving`). Unless a different version of TensorFlow Serving is required, the TensorFlow Serving image shouldn't have to be overridden, since it's only used to load the SavedModel and does not run your Predictor code.*
0 commit comments