Merge branch 'master' into richo/header-injection

.buildkite/core.rayci.yml

@@ -61,7 +61,7 @@ steps:
 
   - label: ":ray: core: python {{matrix.python}} tests ({{matrix.worker_id}})"
     if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
-    tags: 
+    tags:
       - python
       - dashboard
     instance_type: large

.github/CODEOWNERS

@@ -10,17 +10,17 @@
 # Authors responsible for copy-editing of the documentation.
 # NOTE: Add @ray-project/ray-docs to all following docs subdirs.
 /doc/ @ray-project/ray-docs
-/doc/source/use-cases.rst @ericl @pcmoritz
+/doc/source/use-cases.rst @pcmoritz
 
 # ==== Ray core ====
 
 # API compatibility
-/src/ray/protobuf/common.proto @ericl @pcmoritz @raulchen @ray-project/ray-core
-/src/ray/protobuf/gcs.proto @ericl @pcmoritz @raulchen @ray-project/ray-core
-/src/ray/protobuf/gcs_service.proto @ericl @pcmoritz @raulchen @ray-project/ray-core
+/src/ray/protobuf/common.proto @pcmoritz @raulchen @ray-project/ray-core
+/src/ray/protobuf/gcs.proto @pcmoritz @raulchen @ray-project/ray-core
+/src/ray/protobuf/gcs_service.proto @pcmoritz @raulchen @ray-project/ray-core
 
 # Autoscaler
-/python/ray/autoscaler/ @ericl @ray-project/ray-core @architkulkarni @hongchaodeng
+/python/ray/autoscaler/ @ray-project/ray-core @hongchaodeng
 
 # Metrics
 /src/ray/stats/metric_defs.h @ray-project/ray-core
@@ -36,7 +36,7 @@
 /src/ray/gcs/ @ray-project/ray-core
 
 # Dependencies
-/python/setup.py @richardliaw @ericl @edoakes
+/python/setup.py @richardliaw @edoakes @aslonnie
 
 # CI
 /ci/lint/format.sh @ray-project/ray-ci
@@ -49,11 +49,11 @@
 #!/python/ray/rllib/ @ray-project/ray-core
 
 # Java worker.
-/java/dependencies.bzl @kfstorm @raulchen @ericl @WangTaoTheTonic @SongGuyang
-/java/pom.xml @kfstorm @raulchen @ericl @WangTaoTheTonic @SongGuyang
-/java/pom_template.xml @kfstorm @raulchen @ericl @WangTaoTheTonic @SongGuyang
-/java/*/pom_template.xml @kfstorm @raulchen @ericl @WangTaoTheTonic @SongGuyang
-/java/api/ @kfstorm @raulchen @ericl @WangTaoTheTonic @SongGuyang
+/java/dependencies.bzl @kfstorm @raulchen @WangTaoTheTonic @SongGuyang
+/java/pom.xml @kfstorm @raulchen @WangTaoTheTonic @SongGuyang
+/java/pom_template.xml @kfstorm @raulchen @WangTaoTheTonic @SongGuyang
+/java/*/pom_template.xml @kfstorm @raulchen @WangTaoTheTonic @SongGuyang
+/java/api/ @kfstorm @raulchen @WangTaoTheTonic @SongGuyang
 
 # C++ worker
 /cpp/include/ray @SongGuyang @raulchen @kfstorm @ray-project/ray-core
@@ -63,25 +63,25 @@
 
 # Runtime Env
 # TODO(SongGuyang): Add new items to guarantee runtime env API compatibility in multiple languages.
-/src/ray/protobuf/runtime_env_common.proto @SongGuyang @raulchen @edoakes @architkulkarni @ray-project/ray-core
-/src/ray/protobuf/runtime_env_agent.proto @SongGuyang @raulchen @edoakes @architkulkarni @ray-project/ray-core
+/src/ray/protobuf/runtime_env_common.proto @SongGuyang @raulchen @edoakes @ray-project/ray-core
+/src/ray/protobuf/runtime_env_agent.proto @SongGuyang @raulchen @edoakes @ray-project/ray-core
 
 # ==== Libraries and frameworks ====
 
 # Ray data.
-/python/ray/data/ @ericl @scv119 @c21 @amogkam @scottjlee @bveeramani @raulchen @stephanie-wang @omatthew98
-/doc/source/data/ @ericl @scv119 @c21 @amogkam @scottjlee @bveeramani @raulchen @stephanie-wang @omatthew98
+/python/ray/data/ @scottjlee @bveeramani @raulchen @stephanie-wang @omatthew98
+/doc/source/data/ @scottjlee @bveeramani @raulchen @stephanie-wang @omatthew98
 
 # Ray workflows.
-/python/ray/workflow/ @ericl @stephanie-wang @suquark
-/doc/source/workflows/ @ericl @stephanie-wang @suquark @maxpumperla @ray-project/ray-docs
+/python/ray/workflow/ @stephanie-wang
+/doc/source/workflows/ @stephanie-wang @maxpumperla @ray-project/ray-docs
 
 # RLlib.
-/rllib/ @sven1977 @arturniederfahrenhorst @simonsays1980
-/doc/source/rllib/ @sven1977 @arturniederfahrenhorst @maxpumperla @simonsays1980 @ray-project/ray-docs
+/rllib/ @sven1977 @simonsays1980
+/doc/source/rllib/ @sven1977 @maxpumperla @simonsays1980 @ray-project/ray-docs
 
 # Cluster (docs)
-/doc/source/cluster/ @architkulkarni @maxpumperla @pcmoritz @kevin85421 @ray-project/ray-docs
+/doc/source/cluster/ @maxpumperla @pcmoritz @kevin85421 @ray-project/ray-docs
 
 # Tune
 /python/ray/tune/ @hongpeng-guo @justinvyu @matthewdeng @raulchen @woshiyyya
@@ -95,16 +95,16 @@
 /doc/source/serve/ @edoakes @shrekris-anyscale @zcin @GeneDer @akshay-anyscale @ray-project/ray-docs
 
 # ML Docker Dependencies
-/python/requirements/ml/dl-cpu-requirements.txt @amogkam @richardliaw @matthewdeng
-/python/requirements/ml/dl-gpu-requirements.txt @amogkam @richardliaw @matthewdeng
+/python/requirements/ml/dl-cpu-requirements.txt @richardliaw @matthewdeng
+/python/requirements/ml/dl-gpu-requirements.txt @richardliaw @matthewdeng
 
 # Ray symbol export
-/src/ray/ray_version_script.lds @ericl @scv119
-/src/ray/ray_exported_symbols.lds @ericl @scv119
+/src/ray/ray_version_script.lds @aslonnie
+/src/ray/ray_exported_symbols.lds @aslonnie
 
 # Ray usage stats
-/python/ray/_private/usage/ @ericl @richardliaw @rkooo567 @jjyao
-/python/ray/dashboard/modules/usage_stats/ @ericl @richardliaw @rkooo567 @jjyao
+/python/ray/_private/usage/ @richardliaw @rkooo567 @jjyao
+/python/ray/dashboard/modules/usage_stats/ @richardliaw @rkooo567 @jjyao
 
 
 # ==== Build and CI ====
@@ -122,6 +122,6 @@
 
 /release/ray_release @ray-project/ray-ci
 
-/.github/ISSUE_TEMPLATE/ @ericl @stephanie-wang @scv119 @pcmoritz
+/.github/ISSUE_TEMPLATE/ @anyscalesam @aslonnie
 
 /.github/workflows/ @ray-project/ray-ci

.pre-commit-config.yaml

@@ -80,7 +80,7 @@ repos:
           )
         additional_dependencies:
           [
-            types-PyYAML
+            types-PyYAML==6.0.12.2,
           ]
 
   - repo: https://github.com/pycqa/isort

.vale/styles/config/vocabularies/General/accept.txt

@@ -17,3 +17,5 @@ GKE
 namespace
 ARM
 breakpoint
+deduplicate[s]
+deduplication

BUILD.bazel

@@ -513,6 +513,7 @@ ray_cc_library(
         "@boost//:bimap",
         "@com_github_grpc_grpc//src/proto/grpc/health/v1:health_proto",
         "@com_google_absl//absl/container:btree",
+        "//src/ray/util:thread_checker",
     ],
 )
 

README.rst

@@ -137,4 +137,4 @@ Getting Involved
 .. _`StackOverflow`: https://stackoverflow.com/questions/tagged/ray
 .. _`Meetup Group`: https://www.meetup.com/Bay-Area-Ray-Meetup/
 .. _`Twitter`: https://twitter.com/raydistributed
-.. _`Slack`: https://forms.gle/9TSdDYUgxYs8SA9e8
+.. _`Slack`: https://www.ray.io/join-slack?utm_source=github&utm_medium=ray_readme&utm_campaign=getting_involved

ci/env/install-dependencies.sh

@@ -244,9 +244,9 @@ install_pip_packages() {
 
     # For DAG visualization
     requirements_packages+=("pydot")
-    requirements_packages+=("pytesseract")
-    requirements_packages+=("spacy>=3")
-    requirements_packages+=("spacy_langdetect")
+    requirements_packages+=("pytesseract==0.3.13")
+    requirements_packages+=("spacy==3.7.5")
+    requirements_packages+=("spacy_langdetect==0.1.2")
   fi
 
   # Additional RLlib test dependencies.

ci/ray_ci/docker_container.py

@@ -20,8 +20,8 @@
 ]
 GPU_PLATFORM = "cu12.1.1-cudnn8"
 
-PYTHON_VERSIONS_RAY = ["3.9", "3.10", "3.11"]
-PYTHON_VERSIONS_RAY_ML = ["3.9", "3.10"]
+PYTHON_VERSIONS_RAY = ["3.9", "3.10", "3.11", "3.12"]
+PYTHON_VERSIONS_RAY_ML = ["3.9", "3.10", "3.11"]
 ARCHITECTURES_RAY = ["x86_64", "aarch64"]
 ARCHITECTURES_RAY_ML = ["x86_64"]
 
@@ -46,6 +46,15 @@ def __init__(
         upload: bool = False,
     ) -> None:
         assert "RAYCI_CHECKOUT_DIR" in os.environ, "RAYCI_CHECKOUT_DIR not set"
+
+        assert python_version in PYTHON_VERSIONS_RAY
+        assert platform in PLATFORMS_RAY
+        assert architecture in ARCHITECTURES_RAY
+        if image_type == RayType.RAY_ML:
+            assert python_version in PYTHON_VERSIONS_RAY_ML
+            assert platform in PLATFORMS_RAY_ML
+            assert architecture in ARCHITECTURES_RAY_ML
+
         rayci_checkout_dir = os.environ["RAYCI_CHECKOUT_DIR"]
         self.python_version = python_version
         self.platform = platform
@@ -122,13 +131,13 @@ def _get_image_tags(self, external: bool = False) -> List[str]:
         versions = self._get_image_version_tags(external)
 
         platforms = [self.get_platform_tag()]
-        if self.platform == "cpu" and self.image_type == "ray":
+        if self.platform == "cpu" and self.image_type == RayType.RAY:
             # no tag is alias to cpu for ray image
             platforms.append("")
         elif self.platform == GPU_PLATFORM:
             # gpu is alias to cu118 for ray image
             platforms.append("-gpu")
-            if self.image_type == "ray-ml":
+            if self.image_type == RayType.RAY_ML:
                 # no tag is alias to gpu for ray-ml image
                 platforms.append("")
 

ci/ray_ci/test_ray_docker_container.py

@@ -7,6 +7,7 @@
 
 from ci.ray_ci.builder_container import DEFAULT_PYTHON_VERSION
 from ci.ray_ci.container import _DOCKER_ECR_REPO
+from ci.ray_ci.docker_container import GPU_PLATFORM
 from ci.ray_ci.ray_docker_container import RayDockerContainer
 from ci.ray_ci.test_base import RayCITestBase
 from ci.ray_ci.utils import RAY_VERSION
@@ -203,8 +204,8 @@ def test_canonical_tag(self) -> None:
         container = RayDockerContainer(v, "cpu", "ray", "aarch64")
         assert container._get_canonical_tag() == f"{sha}-{pv}-cpu-aarch64"
 
-        container = RayDockerContainer(v, "cu11.8.0-cudnn8", "ray-ml")
-        assert container._get_canonical_tag() == f"{sha}-{pv}-cu118"
+        container = RayDockerContainer(v, GPU_PLATFORM, "ray-ml")
+        assert container._get_canonical_tag() == f"{sha}-{pv}-cu121"
 
         with mock.patch.dict(os.environ, {"BUILDKITE_BRANCH": "releases/1.0.0"}):
             container = RayDockerContainer(v, "cpu", "ray")

doc/BUILD

@@ -467,6 +467,7 @@ doctest(
             "source/rllib/rllib-sample-collection.rst",
         ],
     ),
+    data = ["//rllib:cartpole-v1_large"],
     tags = ["team:rllib"],
 )
 

doc/source/_includes/rllib/new_api_stack.rst

@@ -4,8 +4,4 @@
     The Ray Team plans to transition algorithms, example scripts, and documentation to the new code base
     thereby incrementally replacing the "old API stack" (e.g., ModelV2, Policy, RolloutWorker) throughout the subsequent minor releases leading up to Ray 3.0.
 
-    Note, however, that so far only PPO (single- and multi-agent) and SAC (single-agent only)
-    support the "new API stack" and continue to run by default with the old APIs.
-    You can continue to use the existing custom (old stack) classes.
-
     :doc:`See here </rllib/rllib-new-api-stack>` for more details on how to use the new API stack.

doc/source/_templates/navbar-anyscale.html

@@ -1,4 +1,4 @@
-<a id="try-anyscale-href" href="https://console.anyscale.com">
+<a id="try-anyscale-href" href="https://console.anyscale.com/?utm_source=ray_docs&utm_medium=docs&utm_campaign=navbar">
   <div id="try-anyscale-text">
     <span>Try Ray on Anyscale</span>
   </div>

doc/source/cluster/kubernetes/examples/gpu-training-example.md

@@ -40,10 +40,10 @@ kubectl apply -f https://raw.githubusercontent.com/GoogleCloudPlatform/container
 #   (Method 2) "gcloud container clusters get-credentials <your-cluster-name> --region <your-region> --project <your-project>"
 #   (Method 3) "kubectl config use-context ..."
 
-# Install both CRDs and KubeRay operator v1.0.0.
+# Install both CRDs and KubeRay operator.
 helm repo add kuberay https://ray-project.github.io/kuberay-helm/
 helm repo update
-helm install kuberay-operator kuberay/kuberay-operator --version 1.0.0
+helm install kuberay-operator kuberay/kuberay-operator --version 1.2.2
 
 # Create a Ray cluster
 kubectl apply -f https://raw.githubusercontent.com/ray-project/ray/master/doc/source/cluster/kubernetes/configs/ray-cluster.gpu.yaml
@@ -116,7 +116,7 @@ It is optional.
 # Create the KubeRay operator
 helm repo add kuberay https://ray-project.github.io/kuberay-helm/
 helm repo update
-helm install kuberay-operator kuberay/kuberay-operator --version 1.0.0
+helm install kuberay-operator kuberay/kuberay-operator --version 1.2.2
 
 # Create a Ray cluster
 kubectl apply -f https://raw.githubusercontent.com/ray-project/ray/master/doc/source/cluster/kubernetes/configs/ray-cluster.gpu.yaml

doc/source/cluster/kubernetes/examples/mobilenet-rayservice.md

@@ -19,7 +19,7 @@ Note that the YAML file in this example uses `serveConfigV2`, which is supported
 
 ```sh
 # Download `ray-service.mobilenet.yaml`
-curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.0.0/ray-operator/config/samples/ray-service.mobilenet.yaml
+curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-service.mobilenet.yaml
 
 # Create a RayService
 kubectl apply -f ray-service.mobilenet.yaml

doc/source/cluster/kubernetes/examples/rayjob-batch-inference-example.md

@@ -37,12 +37,12 @@ The KubeRay operator Pod must be on the CPU node if you have set up the taint fo
 
 ## Step 2: Submit the RayJob
 
-Create the RayJob custom resource with [ray-job.batch-inference.yaml](https://github.com/ray-project/kuberay/blob/v1.0.0/ray-operator/config/samples/ray-job.batch-inference.yaml).
+Create the RayJob custom resource with [ray-job.batch-inference.yaml](https://github.com/ray-project/kuberay/blob/v1.2.2/ray-operator/config/samples/ray-job.batch-inference.yaml).
 
 Download the file with `curl`:
 
 ```bash
-curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.0.0/ray-operator/config/samples/ray-job.batch-inference.yaml
+curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-job.batch-inference.yaml
 ```
 
 Note that the `RayJob` spec contains a spec for the `RayCluster`. This tutorial uses a single-node cluster with 4 GPUs. For production use cases, use a multi-node cluster where the head node doesn't have GPUs, so that Ray can automatically schedule GPU workloads on worker nodes which won't interfere with critical Ray processes on the head node.

doc/source/cluster/kubernetes/examples/stable-diffusion-rayservice.md

@@ -18,7 +18,7 @@ Please note that the YAML file in this example uses `serveConfigV2`, which is su
 
 ```sh
 # Step 3.1: Download `ray-service.stable-diffusion.yaml`
-curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.0.0/ray-operator/config/samples/ray-service.stable-diffusion.yaml
+curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-service.stable-diffusion.yaml
 
 # Step 3.2: Create a RayService
 kubectl apply -f ray-service.stable-diffusion.yaml

doc/source/cluster/kubernetes/examples/text-summarizer-rayservice.md

@@ -17,7 +17,7 @@ Please note that the YAML file in this example uses `serveConfigV2`, which is su
 
 ```sh
 # Step 3.1: Download `ray-service.text-summarizer.yaml`
-curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.0.0/ray-operator/config/samples/ray-service.text-summarizer.yaml
+curl -LO https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-service.text-summarizer.yaml
 
 # Step 3.2: Create a RayService
 kubectl apply -f ray-service.text-summarizer.yaml

doc/source/cluster/kubernetes/getting-started/raycluster-quick-start.md

@@ -26,8 +26,8 @@ Deploy the KubeRay operator with the [Helm chart repository](https://github.com/
 helm repo add kuberay https://ray-project.github.io/kuberay-helm/
 helm repo update
 
-# Install both CRDs and KubeRay operator v1.1.1.
-helm install kuberay-operator kuberay/kuberay-operator --version 1.1.1
+# Install both CRDs and KubeRay operator v1.2.2.
+helm install kuberay-operator kuberay/kuberay-operator --version 1.2.2
 
 # Confirm that the operator is running in the namespace `default`.
 kubectl get pods
@@ -46,14 +46,14 @@ Once the KubeRay operator is running, we are ready to deploy a RayCluster. To do
   :::{tab-item} ARM64 (Apple Silicon)
   ```sh
   # Deploy a sample RayCluster CR from the KubeRay Helm chart repo:
-  helm install raycluster kuberay/ray-cluster --version 1.1.1 --set 'image.tag=2.9.0-aarch64'
+  helm install raycluster kuberay/ray-cluster --version 1.2.2 --set 'image.tag=2.9.0-aarch64'
   ```
   :::
 
   :::{tab-item} x86-64 (Intel/Linux)
   ```sh
   # Deploy a sample RayCluster CR from the KubeRay Helm chart repo:
-  helm install raycluster kuberay/ray-cluster --version 1.1.1
+  helm install raycluster kuberay/ray-cluster --version 1.2.2
   ```
   :::
 

doc/source/cluster/kubernetes/getting-started/rayjob-quick-start.md

@@ -6,7 +6,7 @@
 
 * KubeRay v0.6.0 or higher
   * KubeRay v0.6.0 or v1.0.0: Ray 1.10 or higher.
-  * KubeRay v1.1.1 is highly recommended: Ray 2.8.0 or higher. This document is mainly for KubeRay v1.1.1.
+  * KubeRay v1.1.1 or newer is highly recommended: Ray 2.8.0 or higher.
 
 ## What's a RayJob?
 
@@ -78,7 +78,7 @@ Follow the [RayCluster Quickstart](kuberay-operator-deploy) to install the lates
 ## Step 3: Install a RayJob
 
 ```sh
-kubectl apply -f https://raw.githubusercontent.com/ray-project/kuberay/v1.1.1/ray-operator/config/samples/ray-job.sample.yaml
+kubectl apply -f https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-job.sample.yaml
 ```
 
 ## Step 4: Verify the Kubernetes cluster status
@@ -158,13 +158,13 @@ The Python script `sample_code.py` used by `entrypoint` is a simple Ray script t
 ## Step 6: Delete the RayJob
 
 ```sh
-kubectl delete -f https://raw.githubusercontent.com/ray-project/kuberay/v1.1.1/ray-operator/config/samples/ray-job.sample.yaml
+kubectl delete -f https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-job.sample.yaml
 ```
 
 ## Step 7: Create a RayJob with `shutdownAfterJobFinishes` set to true
 
 ```sh
-kubectl apply -f https://raw.githubusercontent.com/ray-project/kuberay/v1.1.1/ray-operator/config/samples/ray-job.shutdown.yaml
+kubectl apply -f https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-job.shutdown.yaml
 ```
 
 The `ray-job.shutdown.yaml` defines a RayJob custom resource with `shutdownAfterJobFinishes: true` and `ttlSecondsAfterFinished: 10`.
@@ -192,7 +192,7 @@ kubectl get raycluster
 
 ```sh
 # Step 10.1: Delete the RayJob
-kubectl delete -f https://raw.githubusercontent.com/ray-project/kuberay/v1.1.1/ray-operator/config/samples/ray-job.shutdown.yaml
+kubectl delete -f https://raw.githubusercontent.com/ray-project/kuberay/v1.2.2/ray-operator/config/samples/ray-job.shutdown.yaml
 
 # Step 10.2: Delete the KubeRay operator
 helm uninstall kuberay-operator