Skip to content

Commit 35f1291

Browse files
committed
Update stable version to 0.24.1
1 parent c4c65fc commit 35f1291

File tree

7 files changed

+43
-43
lines changed

7 files changed

+43
-43
lines changed

docs/aws/install.md

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -82,19 +82,19 @@ The docker images used by the Cortex cluster can also be overridden, although th
8282
8383
<!-- CORTEX_VERSION_BRANCH_STABLE -->
8484
```yaml
85-
image_operator: quay.io/cortexlabs/operator:0.24.0
86-
image_manager: quay.io/cortexlabs/manager:0.24.0
87-
image_downloader: quay.io/cortexlabs/downloader:0.24.0
88-
image_request_monitor: quay.io/cortexlabs/request-monitor:0.24.0
89-
image_cluster_autoscaler: quay.io/cortexlabs/cluster-autoscaler:0.24.0
90-
image_metrics_server: quay.io/cortexlabs/metrics-server:0.24.0
91-
image_inferentia: quay.io/cortexlabs/inferentia:0.24.0
92-
image_neuron_rtd: quay.io/cortexlabs/neuron-rtd:0.24.0
93-
image_nvidia: quay.io/cortexlabs/nvidia:0.24.0
94-
image_fluentd: quay.io/cortexlabs/fluentd:0.24.0
95-
image_statsd: quay.io/cortexlabs/statsd:0.24.0
96-
image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.24.0
97-
image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.24.0
85+
image_operator: quay.io/cortexlabs/operator:0.24.1
86+
image_manager: quay.io/cortexlabs/manager:0.24.1
87+
image_downloader: quay.io/cortexlabs/downloader:0.24.1
88+
image_request_monitor: quay.io/cortexlabs/request-monitor:0.24.1
89+
image_cluster_autoscaler: quay.io/cortexlabs/cluster-autoscaler:0.24.1
90+
image_metrics_server: quay.io/cortexlabs/metrics-server:0.24.1
91+
image_inferentia: quay.io/cortexlabs/inferentia:0.24.1
92+
image_neuron_rtd: quay.io/cortexlabs/neuron-rtd:0.24.1
93+
image_nvidia: quay.io/cortexlabs/nvidia:0.24.1
94+
image_fluentd: quay.io/cortexlabs/fluentd:0.24.1
95+
image_statsd: quay.io/cortexlabs/statsd:0.24.1
96+
image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.24.1
97+
image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.24.1
9898
```
9999
100100
## Advanced

docs/gcp/install.md

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -48,11 +48,11 @@ The docker images used by the Cortex cluster can also be overridden, although th
4848
4949
<!-- CORTEX_VERSION_BRANCH_STABLE -->
5050
```yaml
51-
image_operator: quay.io/cortexlabs/operator:0.24.0
52-
image_manager: quay.io/cortexlabs/manager:0.24.0
53-
image_downloader: quay.io/cortexlabs/downloader:0.24.0
54-
image_statsd: quay.io/cortexlabs/statsd:0.24.0
55-
image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.24.0
56-
image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.24.0
57-
image_pause: quay.io/cortexlabs/pause:0.24.0
51+
image_operator: quay.io/cortexlabs/operator:0.24.1
52+
image_manager: quay.io/cortexlabs/manager:0.24.1
53+
image_downloader: quay.io/cortexlabs/downloader:0.24.1
54+
image_statsd: quay.io/cortexlabs/statsd:0.24.1
55+
image_istio_proxy: quay.io/cortexlabs/istio-proxy:0.24.1
56+
image_istio_pilot: quay.io/cortexlabs/istio-pilot:0.24.1
57+
image_pause: quay.io/cortexlabs/pause:0.24.1
5858
```

docs/guides/self-hosted-images.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ set -euo pipefail
3030
# user set variables
3131
ecr_region="us-west-2"
3232
aws_account_id="620970939130" # example account ID
33-
cortex_version="0.24.0"
33+
cortex_version="0.24.1"
3434

3535
source_registry="quay.io/cortexlabs"
3636
destination_ecr_prefix="cortexlabs"

docs/workloads/batch/configuration.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@
1111
path: <string> # path to a python file with a PythonPredictor class definition, relative to the Cortex root (required)
1212
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
1313
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
14-
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.24.0 or quay.io/cortexlabs/python-predictor-gpu:0.24.0 based on compute)
14+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.24.1 or quay.io/cortexlabs/python-predictor-gpu:0.24.1 based on compute)
1515
env: <string: string> # dictionary of environment variables
1616
networking:
1717
endpoint: <string> # the endpoint for the API (default: <api_name>)
@@ -44,8 +44,8 @@
4444
batch_interval: <duration> # the maximum amount of time to spend waiting for additional requests before running inference on the batch of requests
4545
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
4646
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
47-
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.24.0)
48-
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu:0.24.0 or quay.io/cortexlabs/tensorflow-serving-cpu:0.24.0 based on compute)
47+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.24.1)
48+
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu:0.24.1 or quay.io/cortexlabs/tensorflow-serving-cpu:0.24.1 based on compute)
4949
env: <string: string> # dictionary of environment variables
5050
networking:
5151
endpoint: <string> # the endpoint for the API (default: <api_name>)
@@ -74,7 +74,7 @@
7474
...
7575
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (can be overridden by config passed in job submission) (optional)
7676
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
77-
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu:0.24.0 or quay.io/cortexlabs/onnx-predictor-cpu:0.24.0 based on compute)
77+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu:0.24.1 or quay.io/cortexlabs/onnx-predictor-cpu:0.24.1 based on compute)
7878
env: <string: string> # dictionary of environment variables
7979
networking:
8080
endpoint: <string> # the endpoint for the API (default: <api_name>)

docs/workloads/realtime/configuration.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@
2222
threads_per_process: <int> # the number of threads per process (default: 1)
2323
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (optional)
2424
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
25-
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.24.0 or quay.io/cortexlabs/python-predictor-gpu:0.24.0 based on compute)
25+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/python-predictor-cpu:0.24.1 or quay.io/cortexlabs/python-predictor-gpu:0.24.1 based on compute)
2626
env: <string: string> # dictionary of environment variables
2727
networking:
2828
endpoint: <string> # the endpoint for the API (aws only) (default: <api_name>)
@@ -82,8 +82,8 @@
8282
threads_per_process: <int> # the number of threads per process (default: 1)
8383
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (optional)
8484
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
85-
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.24.0)
86-
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu:0.24.0 or quay.io/cortexlabs/tensorflow-serving-cpu:0.24.0 based on compute)
85+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/tensorflow-predictor:0.24.1)
86+
tensorflow_serving_image: <string> # docker image to use for the TensorFlow Serving container (default: quay.io/cortexlabs/tensorflow-serving-gpu:0.24.1 or quay.io/cortexlabs/tensorflow-serving-cpu:0.24.1 based on compute)
8787
env: <string: string> # dictionary of environment variables
8888
networking:
8989
endpoint: <string> # the endpoint for the API (aws only) (default: <api_name>)
@@ -138,7 +138,7 @@
138138
threads_per_process: <int> # the number of threads per process (default: 1)
139139
config: <string: value> # arbitrary dictionary passed to the constructor of the Predictor (optional)
140140
python_path: <string> # path to the root of your Python folder that will be appended to PYTHONPATH (default: folder containing cortex.yaml)
141-
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu:0.24.0 or quay.io/cortexlabs/onnx-predictor-cpu:0.24.0 based on compute)
141+
image: <string> # docker image to use for the Predictor (default: quay.io/cortexlabs/onnx-predictor-gpu:0.24.1 or quay.io/cortexlabs/onnx-predictor-cpu:0.24.1 based on compute)
142142
env: <string: string> # dictionary of environment variables
143143
networking:
144144
endpoint: <string> # the endpoint for the API (aws only) (default: <api_name>)

docs/workloads/system-packages.md

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -47,19 +47,19 @@ mkdir my-api && cd my-api && touch Dockerfile
4747
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:
4848

4949
<!-- CORTEX_VERSION_BRANCH_STABLE x12 -->
50-
* Python Predictor (CPU): `quay.io/cortexlabs/python-predictor-cpu-slim:0.24.0`
50+
* Python Predictor (CPU): `quay.io/cortexlabs/python-predictor-cpu-slim:0.24.1`
5151
* Python Predictor (GPU): choose one of the following:
52-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda10.0-cudnn7`
53-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda10.1-cudnn7`
54-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda10.1-cudnn8`
55-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda10.2-cudnn7`
56-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda10.2-cudnn8`
57-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda11.0-cudnn8`
58-
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.0-cuda11.1-cudnn8`
59-
* Python Predictor (Inferentia): `quay.io/cortexlabs/python-predictor-inf-slim:0.24.0`
60-
* TensorFlow Predictor (CPU, GPU, Inferentia): `quay.io/cortexlabs/tensorflow-predictor-slim:0.24.0`
61-
* ONNX Predictor (CPU): `quay.io/cortexlabs/onnx-predictor-cpu-slim:0.24.0`
62-
* ONNX Predictor (GPU): `quay.io/cortexlabs/onnx-predictor-gpu-slim:0.24.0`
52+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda10.0-cudnn7`
53+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda10.1-cudnn7`
54+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda10.1-cudnn8`
55+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda10.2-cudnn7`
56+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda10.2-cudnn8`
57+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda11.0-cudnn8`
58+
* `quay.io/cortexlabs/python-predictor-gpu-slim:0.24.1-cuda11.1-cudnn8`
59+
* Python Predictor (Inferentia): `quay.io/cortexlabs/python-predictor-inf-slim:0.24.1`
60+
* TensorFlow Predictor (CPU, GPU, Inferentia): `quay.io/cortexlabs/tensorflow-predictor-slim:0.24.1`
61+
* ONNX Predictor (CPU): `quay.io/cortexlabs/onnx-predictor-cpu-slim:0.24.1`
62+
* ONNX Predictor (GPU): `quay.io/cortexlabs/onnx-predictor-gpu-slim:0.24.1`
6363

6464
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.
6565

@@ -69,7 +69,7 @@ The sample Dockerfile below inherits from Cortex's Python CPU serving image, and
6969
```dockerfile
7070
# Dockerfile
7171

72-
FROM quay.io/cortexlabs/python-predictor-cpu-slim:0.24.0
72+
FROM quay.io/cortexlabs/python-predictor-cpu-slim:0.24.1
7373

7474
RUN apt-get update \
7575
&& apt-get install -y tree \

get-cli.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@
1616

1717
set -e
1818

19-
CORTEX_VERSION_BRANCH_STABLE=0.24.0
19+
CORTEX_VERSION_BRANCH_STABLE=0.24.1
2020
CORTEX_INSTALL_PATH="${CORTEX_INSTALL_PATH:-/usr/local/bin/cortex}"
2121

2222
# replace ~ with the home directory path

0 commit comments

Comments
 (0)