Comments (1)
After using a newer ray version (2.9.0), the issue was solved. Here is the yaml I used:
# Make sure to increase resource requests and limits before using this example in production.
# For examples with more realistic resource configuration, see
# ray-cluster.complete.large.yaml and
# ray-cluster.autoscaler.large.yaml.
apiVersion: ray.io/v1alpha1
kind: RayService
metadata:
name: rayservice-sample
spec:
serviceUnhealthySecondThreshold: 900 # Config for the health check threshold for Ray Serve applications. Default value is 900.
deploymentUnhealthySecondThreshold: 300 # Config for the health check threshold for Ray dashboard agent. Default value is 300.
# serveConfigV2 takes a yaml multi-line scalar, which should be a Ray Serve multi-application config. See https://docs.ray.io/en/latest/serve/multi-app.html.
# Only one of serveConfig and serveConfigV2 should be used.
serveConfigV2: |
applications:
- name: text_ml_app
import_path: text_ml.app
route_prefix: /summarize_translate
runtime_env:
working_dir: "https://github.com/ray-project/serve_config_examples/archive/36862c251615e258a58285934c7c41cffd1ee3b7.zip"
pip:
- torch
- transformers
deployments:
- name: Translator
num_replicas: 1
ray_actor_options:
num_cpus: 0.2
user_config:
language: french
- name: Summarizer
num_replicas: 1
ray_actor_options:
num_cpus: 0.2
rayClusterConfig:
rayVersion: '2.9.0' # should match the Ray version in the image of the containers
######################headGroupSpecs#################################
# Ray head pod template.
headGroupSpec:
# The `rayStartParams` are used to configure the `ray start` command.
# See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
# See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
rayStartParams:
dashboard-host: '0.0.0.0'
#pod template
template:
spec:
containers:
- name: ray-head
image: rayproject/ray:2.9.0
resources:
limits:
cpu: 1
memory: 2Gi
requests:
cpu: 1
memory: 2Gi
ports:
- containerPort: 6379
name: gcs-server
- containerPort: 8265 # Ray dashboard
name: dashboard
- containerPort: 10001
name: client
- containerPort: 8000
name: serve
workerGroupSpecs:
# the pod replicas in this group typed worker
- replicas: 1
minReplicas: 1
maxReplicas: 5
# logical group name, for this called small-group, also can be functional
groupName: small-group
# The `rayStartParams` are used to configure the `ray start` command.
# See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
# See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
rayStartParams: {}
#pod template
template:
spec:
containers:
- name: ray-worker # must consist of lower case alphanumeric characters or '-', and must start and end with an alphanumeric character (e.g. 'my-name', or '123-abc'
image: rayproject/ray:2.9.0
lifecycle:
preStop:
exec:
command: ["/bin/sh","-c","ray stop"]
resources:
limits:
cpu: "1"
memory: "2Gi"
requests:
cpu: "500m"
memory: "2Gi"
from ray.
Related Issues (20)
- Ray-cluster setup results: proxyconnect tcp: dial tcp 127.0.0.1:1082: connect: connection refused
- Unexpected node deaths cannot be recovered from checkpoints
- Release test single_node_oom.aws failed HOT 1
- [Core] "Edit on Github" Links in documentation broken HOT 1
- CI test windows://python/ray/tests:test_streaming_generator is flaky HOT 1
- [Tune] Cannot run the QuickStart example code on windows after installing Ray in conda enviroment, reporting FileNotFoundError
- [Core] object can not be get because the owner exits HOT 1
- [Core] Ray cpp example fails with error HOT 1
- [Ray CORE] Gitlab integration with authentication HOT 2
- [Ray Dashboard] Log output cannot be viewed after the node is scaled down
- How Does Ray Support Application Upgrade? HOT 1
- [Core] Slowdown of task execution when many tasks are started at the same time.
- [RLlib] `on_episode_end` callback is not called until after env is reset in single-agent environments HOT 2
- CI test linux://python/ray/serve/tests:test_autoscaling_policy_with_queue_len_cache_disabled is consistently_failing HOT 1
- [Core][aDAG] Make it easily compatible with cuda graph
- [Core][aDAG] Allow to control serialization
- [Core] Failed to start head in container. HOT 1
- [Data] `map_batches` fails with "ValueError: cannot reshape array of size 6 into shape (1, 2)" HOT 1
- CI test linux://python/ray/serve/tests:test_autoscaling_policy is flaky HOT 1
- CI test linux://python/ray/serve/tests:test_autoscaling_policy_with_queue_len_cache_disabled is flaky HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ray.