Merge branch 'master' into deflak-test-metrics

BUILD.bazel

@@ -2525,6 +2525,7 @@ filegroup(
         "//src/ray/protobuf:runtime_env_agent_py_proto",
         "//src/ray/protobuf:runtime_env_common_py_proto",
         "//src/ray/protobuf:usage_py_proto",
+        "//src/ray/protobuf:export_event_py_proto",
     ],
 )
 
@@ -2618,6 +2619,9 @@ genrule(
         # of experimental.
         autoscale_files=(`ls python/ray/core/generated/instance_manager_pb2*.py`)
         sed -i -E 's/from ..experimental/from ./' "$${autoscale_files[@]}"
+        # Help the generated export api files to have the correct module
+        export_api_files=(`ls python/ray/core/generated/export*_pb2*.py`)
+        sed -i -E 's/from ..export_api/from ./' "$${export_api_files[@]}"
         echo "$${PWD}" > $@
     """,
     local = 1,

ci/docker/base.gpu.Dockerfile

@@ -39,7 +39,7 @@ RUN ln -s /usr/bin/clang-format-12 /usr/bin/clang-format && \
     ln -s /usr/bin/clang-tidy-12 /usr/bin/clang-tidy && \
     ln -s /usr/bin/clang-12 /usr/bin/clang
 
-RUN curl -o- https://get.docker.com | sh
+RUN curl -o- https://get.docker.com | sh -s -- --version 27.2
 
 # System conf for tests
 RUN locale -a

ci/docker/base.test.Dockerfile

@@ -41,7 +41,7 @@ ln -s /usr/bin/clang-12 /usr/bin/clang
 
 EOF
 
-RUN curl -o- https://get.docker.com | sh
+RUN curl -o- https://get.docker.com | sh -s -- --version 27.2
 
 # System conf for tests
 RUN locale -a

ci/docker/min.build.Dockerfile

@@ -36,14 +36,11 @@ elif [[ "${EXTRA_DEPENDENCY}" == "ml" ]]; then
 elif [[ "${EXTRA_DEPENDENCY}" == "default" ]]; then
   pip-compile -o min_requirements.txt python/setup.py --extra default
 elif [[ "${EXTRA_DEPENDENCY}" == "serve" ]]; then
-  pip-compile -o min_requirements.txt python/setup.py --extra serve
+  pip-compile -o min_requirements.txt python/setup.py --extra serve-grpc
 fi
 
 if [[ -f min_requirements.txt ]]; then
   pip install -r min_requirements.txt
 fi
 
 EOF
-
-
-

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/data/monitoring-your-workload.rst

@@ -5,10 +5,40 @@ Monitoring Your Workload
 
 This section helps you debug and monitor the execution of your :class:`~ray.data.Dataset` by viewing the:
 
+* :ref:`Ray Data progress bars <ray-data-progress-bars>`
 * :ref:`Ray Data dashboard <ray-data-dashboard>`
 * :ref:`Ray Data logs <ray-data-logs>`
 * :ref:`Ray Data stats <ray-data-stats>`
 
+.. _ray-data-progress-bars:
+
+Ray Data progress bars
+----------------------
+
+When you execute a :class:`~ray.data.Dataset`, Ray Data displays a set of progress bars in the console. These progress bars show various execution and progress-related metrics, including the number of rows completed/remaining, resource usage, and task/actor status. See the annotated image for a breakdown of how to interpret the progress bar outputs: 
+
+.. image:: images/dataset-progress-bar.png
+   :align: center
+
+
+Some additional notes on progress bars:
+
+* The progress bars are updated every second; resource usage, metrics, and task/actor status may take up to 5 seconds to update.
+* When the tasks section contains the label `[backpressure]`, it indicates that the operator is *backpressured*, meaning that the operator won't submit more tasks until the downstream operator is ready to accept more data.
+* The global resource usage is the sum of resources used by all operators, active and requested (includes pending scheduling and pending node assignment).
+
+Configuring the progress bar
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Depending on your use case, you may not be interested in the full progress bar output, or wish to turn them off altogether. Ray Data provides several ways to accomplish this:
+
+* Disabling operator-level progress bars: Set `DataContext.get_current().enable_operator_progress_bars = False`. This only shows the global progress bar, and omits operator-level progress bars.
+* Disabling all progress bars: Set `DataContext.get_current().enable_progress_bars = False`. This disables all progress bars from Ray Data related to dataset execution.
+* Disabling `ray_tqdm`: Set `DataContext.get_current().use_ray_tqdm = False`. This configures Ray Data to use the base `tqdm` library instead of the custom distributed `tqdm` implementation, which could be useful when debugging logging issues in a distributed setting.
+
+For operator names longer than a threshold of 100 characters, Ray Data truncates the names by default, to prevent the case when the operator names are long and the progress bar is too wide to fit on the screen.
+
+* To turn off this behavior and show the full operator name, set `DataContext.get_current().enable_progress_bar_name_truncation = False`.
+* To change the threshold of truncating the name, update the constant `ray.data._internal.progress_bar.ProgressBar.MAX_NAME_LENGTH = 42`.
 
 .. _ray-data-dashboard:
 

doc/source/ray-overview/installation.rst

@@ -431,7 +431,7 @@ We publish the dependencies that are installed in our ``ray`` Docker images for
     .. tab-item:: ray (Python 3.9)
         :sync: ray (Python 3.9)
 
-        Ray version: nightly (`679989c <https://github.com/ray-project/ray/commit/679989c00774c7fa0b94db711ce8eedda2190765>`_)
+        Ray version: nightly (`d2982b7 <https://github.com/ray-project/ray/commit/d2982b7b4f0e10e2f6143f932803017728387b73>`_)
 
         .. literalinclude:: ./pip_freeze_ray-py39-cpu.txt
 

doc/source/ray-overview/pip_freeze_ray-ml-py39-cpu.txt

@@ -40,7 +40,7 @@ ax-platform==0.3.2
 azure-cli-core==2.40.0
 azure-cli-telemetry==1.0.8
 azure-common==1.1.28
-azure-core==1.30.2
+azure-core==1.31.0
 azure-identity==1.10.0
 azure-mgmt-compute==23.1.0
 azure-mgmt-core==1.4.0
@@ -61,11 +61,11 @@ boto3==1.26.76
 botocore==1.29.76
 botorch==0.8.5
 Brotli @ file:///croot/brotli-split_1714483155106/work
-build==1.2.1
+build==1.2.2
 cached-property==1.5.2
 cachetools==5.3.2
 certifi==2023.11.17
-cffi @ file:///croot/cffi_1714483155441/work
+cffi==1.16.0
 charset-normalizer==3.3.2
 chess==1.7.0
 chex==0.1.7
@@ -235,7 +235,7 @@ markdown-it-py==2.2.0
 MarkupSafe==2.1.3
 matplotlib==3.7.4
 matplotlib-inline==0.1.6
-mdit-py-plugins==0.4.1
+mdit-py-plugins==0.4.2
 mdurl==0.1.2
 MedPy==0.4.0
 memray==1.10.0
@@ -287,7 +287,7 @@ nvidia-curand-cu12==10.3.2.106
 nvidia-cusolver-cu12==11.4.5.107
 nvidia-cusparse-cu12==12.1.0.106
 nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.20
+nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
 oauth2client==4.1.3
 oauthlib==3.2.2
@@ -299,9 +299,9 @@ opencensus-context==0.1.3
 opencv-python==4.8.1.78
 opentelemetry-api==1.1.0
 opentelemetry-exporter-otlp==1.1.0
-opentelemetry-exporter-otlp-proto-common==1.26.0
+opentelemetry-exporter-otlp-proto-common==1.27.0
 opentelemetry-exporter-otlp-proto-grpc==1.1.0
-opentelemetry-exporter-otlp-proto-http==1.26.0
+opentelemetry-exporter-otlp-proto-http==1.27.0
 opentelemetry-proto==1.1.0
 opentelemetry-sdk==1.1.0
 opentelemetry-semantic-conventions==0.20b0
@@ -376,7 +376,7 @@ PyYAML==6.0.1
 pyzmq==26.0.3
 qpd==0.4.4
 querystring-parser==1.2.4
-ray @ file:///home/ray/ray-3.0.0.dev0-cp39-cp39-manylinux2014_x86_64.whl#sha256=12b22b71023ef14a77ef7df4bbea91a302faeb76924ff36ad33547071720cfe4
+ray @ file:///home/ray/ray-3.0.0.dev0-cp39-cp39-manylinux2014_x86_64.whl#sha256=5d1e3379c141110a198d1405999bd3937976d0d003ba039a69c970407a05872c
 recsim==0.2.4
 redis==3.5.3
 referencing==0.35.1
@@ -442,7 +442,7 @@ tensorflow-probability==0.23.0
 tensorstore==0.1.63
 termcolor==2.4.0
 terminado==0.18.1
-textual==0.77.0
+textual==0.80.0
 tf-slim==1.1.0
 tf2onnx==1.15.1
 threadpoolctl==3.1.0
@@ -474,7 +474,7 @@ typeguard==2.13.3
 typer==0.12.3
 types-python-dateutil==2.9.0.20240316
 typing_extensions==4.8.0
-tzdata==2024.1
+tzdata==2024.2
 uc-micro-py==1.0.3
 uri-template==1.3.0
 uritemplate==3.0.1

doc/source/ray-overview/pip_freeze_ray-py39-cpu.txt

@@ -13,7 +13,7 @@ attrs==21.4.0
 azure-cli-core==2.40.0
 azure-cli-telemetry==1.0.8
 azure-common==1.1.28
-azure-core==1.30.2
+azure-core==1.31.0
 azure-identity==1.10.0
 azure-mgmt-compute==23.1.0
 azure-mgmt-core==1.4.0
@@ -27,7 +27,7 @@ botocore==1.29.165
 Brotli @ file:///croot/brotli-split_1714483155106/work
 cachetools==5.3.2
 certifi==2023.11.17
-cffi @ file:///croot/cffi_1714483155441/work
+cffi==1.16.0
 charset-normalizer==3.3.2
 click==8.1.7
 cloudpickle==2.2.0
@@ -122,15 +122,15 @@ pydantic_core==2.14.1
 Pygments==2.18.0
 PyJWT==2.9.0
 PyNaCl==1.5.0
-pyOpenSSL==22.1.0
+pyOpenSSL==23.0.0
 pyparsing==3.1.4
 pyrsistent==0.20.0
 PySocks @ file:///tmp/build/80754af9/pysocks_1605305812635/work
 python-dateutil==2.8.2
 python-dotenv==1.0.1
 pytz==2022.7.1
 PyYAML==6.0.1
-ray @ file:///home/ray/ray-3.0.0.dev0-cp39-cp39-manylinux2014_x86_64.whl#sha256=3ffd977059119b997d03fcf4914449c5109cef7f65cfcb84957b53ff741b004b
+ray @ file:///home/ray/ray-3.0.0.dev0-cp39-cp39-manylinux2014_x86_64.whl#sha256=29398ae540c9e4047328710b6bd8cce2cc9f4f82deb75db76a8632d6f602dea5
 redis==3.5.3
 requests==2.31.0
 requests-oauthlib==2.0.0
@@ -149,7 +149,7 @@ starlette==0.36.3
 tabulate==0.9.0
 tensorboardX==2.6.2.2
 tifffile==2024.7.21
-tqdm @ file:///croot/tqdm_1716395931952/work
+tqdm @ file:///croot/tqdm_1724853939799/work
 typer==0.12.3
 typing_extensions==4.8.0
 uritemplate==3.0.1

doc/source/rllib/doc_code/catalog_guide.py

@@ -113,7 +113,10 @@ def __init__(self, *args, **kwargs):
 
 config = (
     PPOConfig()
-    .api_stack(enable_rl_module_and_learner=True)
+    .api_stack(
+        enable_rl_module_and_learner=True,
+        enable_env_runner_and_connector_v2=True,
+    )
     .environment("CartPole-v1")
     .framework("torch")
 )

doc/source/rllib/doc_code/checkpoints.py

@@ -4,12 +4,12 @@
 import tempfile
 
 from ray.rllib.algorithms.algorithm import Algorithm
-from ray.rllib.algorithms.dqn import DQNConfig
+from ray.rllib.algorithms.ppo import PPOConfig
 from ray.rllib.utils.checkpoints import convert_to_msgpack_checkpoint
 
 
 # Base config used for both pickle-based checkpoint and msgpack-based one.
-config = DQNConfig().environment("CartPole-v1")
+config = PPOConfig().environment("CartPole-v1").env_runners(num_env_runners=0)
 # Build algorithm object.
 algo1 = config.build()