[train][2.7][3/n] cherry-picks for documentations, tests, examples

.buildkite/pipeline.ml.yml

@@ -42,7 +42,7 @@
  - ./ci/env/env_info.sh
  - ./ci/run/run_bazel_test_with_sharding.sh
  --config=ci $(./ci/run/bazel_export_options)
- --test_tag_filters=-gpu_only,-gpu,-minimal,-tune,-doctest
+ --test_tag_filters=-gpu_only,-gpu,-minimal,-tune,-doctest,-needs_credentials
  python/ray/train/...
 
 - label: ":steam_locomotive: :octopus: Train + Tune tests and examples"
@@ -52,8 +52,20 @@
  - cleanup() { if [ "${BUILDKITE_PULL_REQUEST}" = "false" ]; then ./ci/build/upload_build_info.sh; fi }; trap cleanup EXIT
  - TRAIN_TESTING=1 TUNE_TESTING=1 ./ci/env/install-dependencies.sh
  - ./ci/env/env_info.sh
- - bazel test --config=ci $(./ci/run/bazel_export_options) --build_tests_only --test_tag_filters=tune,-gpu_only,-ray_air,-gpu,-doctest python/ray/train/...
-
+ - bazel test --config=ci $(./ci/run/bazel_export_options) --build_tests_only --test_tag_filters=tune,-gpu_only,-ray_air,-gpu,-doctest,-needs_credentials python/ray/train/...
+
+# - label: ":train: :key: Train examples with authentication"
+# conditions: ["NO_WHEELS_REQUIRED", "RAY_CI_TRAIN_AFFECTED", "RAY_CI_BRANCH_BUILD"]
+# instance_size: medium
+# commands:
+# - if [ "$BUILDKITE_PULL_REQUEST" != "false" ]; then exit 0; fi
+# - cleanup() { if [ "${BUILDKITE_PULL_REQUEST}" = "false" ]; then ./ci/build/upload_build_info.sh; fi }; trap cleanup EXIT
+# - TRAIN_TESTING=1 ./ci/env/install-dependencies.sh
+# - ./ci/env/env_info.sh
+# - credentials=$(python ./ci/env/setup_credentials.py)
+# - credential_exit_code=$$?
+# - if [ $credential_exit_code -eq 0 ]; then echo "Credentials are fetched successfully"; bazel test --config=ci $(./ci/run/bazel_export_options) --build_tests_only --test_tag_filters=needs_credentials 
+# python/ray/train/... $credentials; else echo "Credentials cannot be fetched"; exit 1; fi
 
 - label: ":brain: RLlib: Benchmarks (Torch 2.x)"
  conditions: ["NO_WHEELS_REQUIRED", "RAY_CI_RLLIB_AFFECTED"]

ci/env/setup_credentials.py

@@ -0,0 +1,50 @@
+"""
+This script sets up credentials for some services in the
+CI environment.
+This prints out credentials in the following format, to be ingested
+by as bazel test envs.
+--test_env=WANDB_API_KEY=abcd --test_env=COMET_API_KEY=efgh
+"""
+import boto3
+import json
+import sys
+
+AWS_AIR_SECRETS_ARN = (
+ "arn:aws:secretsmanager:us-west-2:029272617770:secret:"
+ "oss-ci/ray-air-test-secrets20221014164754935800000002-UONblX"
+)
+
+
+def get_ray_air_secrets(client):
+ raw_string = client.get_secret_value(SecretId=AWS_AIR_SECRETS_ARN)["SecretString"]
+ return json.loads(raw_string)
+
+
+SERVICES = {
+ "wandb_key": "WANDB_API_KEY",
+ "comet_ml_token": "COMET_API_KEY",
+}
+
+
+def main():
+
+ try:
+ client = boto3.client("secretsmanager", region_name="us-west-2")
+ ray_air_secrets = get_ray_air_secrets(client)
+ except Exception as e:
+ print(f"Could not get Ray AIR secrets: {e}")
+ sys.exit(1)
+ return
+
+ print(
+ " ".join(
+ [
+ f"--test_env={SERVICES[key]}={ray_air_secrets[key]}"
+ for key in SERVICES.keys()
+ ]
+ )
+ )
+
+
+if __name__ == "__main__":
+ main()

doc/BUILD

@@ -196,18 +196,6 @@ py_test_run_all_subdirectory(
  tags = ["exclusive", "team:rllib"],
 )
 
-# --------------------------------------------------------------------
-# Test all doc/source/ray-air/doc_code code included in rst/md files.
-# --------------------------------------------------------------------
-
-py_test_run_all_subdirectory(
- size = "large",
- include = ["source/ray-air/doc_code/*.py"],
- exclude = [],
- extra_srcs = [],
- tags = ["exclusive", "team:ml"],
-)
-
 # --------------------------------------------------------------------
 # Test all doc/source/train/doc_code code included in rst/md files.
 # --------------------------------------------------------------------

doc/source/_toc.yml

@@ -386,17 +386,5 @@ parts:
  - file: cluster/usage-stats
  - file: ray-references/glossary
 
- - file: ray-contribute/stability
+ - file: ray-contribute/index
  title: Developer Guides
- sections:
- - file: ray-contribute/getting-involved
- sections:
- - file: ray-contribute/development
- - file: ray-contribute/docs
- - file: ray-contribute/writing-code-snippets
- - file: ray-contribute/fake-autoscaler
- - file: ray-core/examples/testing-tips
- - file: ray-contribute/debugging.rst
- - file: ray-contribute/profiling.rst
- - file: ray-core/configure
- - file: ray-contribute/whitepaper

doc/source/data/examples/batch_training.ipynb

@@ -85,72 +85,9 @@
  },
  {
  "cell_type": "code",
- "execution_count": 2,
+ "execution_count": null,
  "metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "2022-12-08 17:04:06,689\tINFO worker.py:1223 -- Using address localhost:9031 set in the environment variable RAY_ADDRESS\n",
- "2022-12-08 17:04:06,691\tINFO worker.py:1333 -- Connecting to existing Ray cluster at address: 172.31.174.62:9031...\n",
- "2022-12-08 17:04:06,700\tINFO worker.py:1509 -- Connected to Ray cluster. View the dashboard at \u001b[1m\u001b[32mhttps://console.anyscale-staging.com/api/v2/sessions/ses_gyl6mbksa8xt7b149ib6abld/services?redirect_to=dashboard \u001b[39m\u001b[22m\n"
- ]
- },
- {
- "data": {
- "text/html": [
- "<div>\n",
- " <div style=\"margin-left: 50px;display: flex;flex-direction: row;align-items: center\">\n",
- " <h3 style=\"color: var(--jp-ui-font-color0)\">Ray</h3>\n",
- " <svg version=\"1.1\" id=\"ray\" width=\"3em\" viewBox=\"0 0 144.5 144.6\" style=\"margin-left: 3em;margin-right: 3em\">\n",
- " <g id=\"layer-1\">\n",
- " <path fill=\"#00a2e9\" class=\"st0\" d=\"M97.3,77.2c-3.8-1.1-6.2,0.9-8.3,5.1c-3.5,6.8-9.9,9.9-17.4,9.6S58,88.1,54.8,81.2c-1.4-3-3-4-6.3-4.1\n",
- " c-5.6-0.1-9.9,0.1-13.1,6.4c-3.8,7.6-13.6,10.2-21.8,7.6C5.2,88.4-0.4,80.5,0,71.7c0.1-8.4,5.7-15.8,13.8-18.2\n",
- " c8.4-2.6,17.5,0.7,22.3,8c1.3,1.9,1.3,5.2,3.6,5.6c3.9,0.6,8,0.2,12,0.2c1.8,0,1.9-1.6,2.4-2.8c3.5-7.8,9.7-11.8,18-11.9\n",
- " c8.2-0.1,14.4,3.9,17.8,11.4c1.3,2.8,2.9,3.6,5.7,3.3c1-0.1,2,0.1,3,0c2.8-0.5,6.4,1.7,8.1-2.7s-2.3-5.5-4.1-7.5\n",
- " c-5.1-5.7-10.9-10.8-16.1-16.3C84,38,81.9,37.1,78,38.3C66.7,42,56.2,35.7,53,24.1C50.3,14,57.3,2.8,67.7,0.5\n",
- " C78.4-2,89,4.7,91.5,15.3c0.1,0.3,0.1,0.5,0.2,0.8c0.7,3.4,0.7,6.9-0.8,9.8c-1.7,3.2-0.8,5,1.5,7.2c6.7,6.5,13.3,13,19.8,19.7\n",
- " c1.8,1.8,3,2.1,5.5,1.2c9.1-3.4,17.9-0.6,23.4,7c4.8,6.9,4.6,16.1-0.4,22.9c-5.4,7.2-14.2,9.9-23.1,6.5c-2.3-0.9-3.5-0.6-5.1,1.1\n",
- " c-6.7,6.9-13.6,13.7-20.5,20.4c-1.8,1.8-2.5,3.2-1.4,5.9c3.5,8.7,0.3,18.6-7.7,23.6c-7.9,5-18.2,3.8-24.8-2.9\n",
- " c-6.4-6.4-7.4-16.2-2.5-24.3c4.9-7.8,14.5-11,23.1-7.8c3,1.1,4.7,0.5,6.9-1.7C91.7,98.4,98,92.3,104.2,86c1.6-1.6,4.1-2.7,2.6-6.2\n",
- " c-1.4-3.3-3.8-2.5-6.2-2.6C99.8,77.2,98.9,77.2,97.3,77.2z M72.1,29.7c5.5,0.1,9.9-4.3,10-9.8c0-0.1,0-0.2,0-0.3\n",
- " C81.8,14,77,9.8,71.5,10.2c-5,0.3-9,4.2-9.3,9.2c-0.2,5.5,4,10.1,9.5,10.3C71.8,29.7,72,29.7,72.1,29.7z M72.3,62.3\n",
- " c-5.4-0.1-9.9,4.2-10.1,9.7c0,0.2,0,0.3,0,0.5c0.2,5.4,4.5,9.7,9.9,10c5.1,0.1,9.9-4.7,10.1-9.8c0.2-5.5-4-10-9.5-10.3\n",
- " C72.6,62.3,72.4,62.3,72.3,62.3z M115,72.5c0.1,5.4,4.5,9.7,9.8,9.9c5.6-0.2,10-4.8,10-10.4c-0.2-5.4-4.6-9.7-10-9.7\n",
- " c-5.3-0.1-9.8,4.2-9.9,9.5C115,72.1,115,72.3,115,72.5z M19.5,62.3c-5.4,0.1-9.8,4.4-10,9.8c-0.1,5.1,5.2,10.4,10.2,10.3\n",
- " c5.6-0.2,10-4.9,9.8-10.5c-0.1-5.4-4.5-9.7-9.9-9.6C19.6,62.3,19.5,62.3,19.5,62.3z M71.8,134.6c5.9,0.2,10.3-3.9,10.4-9.6\n",
- " c0.5-5.5-3.6-10.4-9.1-10.8c-5.5-0.5-10.4,3.6-10.8,9.1c0,0.5,0,0.9,0,1.4c-0.2,5.3,4,9.8,9.3,10\n",
- " C71.6,134.6,71.7,134.6,71.8,134.6z\"/>\n",
- " </g>\n",
- " </svg>\n",
- " <table>\n",
- " <tr>\n",
- " <td style=\"text-align: left\"><b>Python version:</b></td>\n",
- " <td style=\"text-align: left\"><b>3.8.5</b></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <td style=\"text-align: left\"><b>Ray version:</b></td>\n",
- " <td style=\"text-align: left\"><b> 2.0.0</b></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <td style=\"text-align: left\"><b>Dashboard:</b></td>\n",
- " <td style=\"text-align: left\"><b><a href=\"http:https://console.anyscale-staging.com/api/v2/sessions/ses_gyl6mbksa8xt7b149ib6abld/services?redirect_to=dashboard\" target=\"_blank\">http:https://console.anyscale-staging.com/api/v2/sessions/ses_gyl6mbksa8xt7b149ib6abld/services?redirect_to=dashboard</a></b></td>\n",
- "</tr>\n",
- "\n",
- " </table>\n",
- " </div>\n",
- "</div>\n"
- ],
- "text/plain": [
- "RayContext(dashboard_url='console.anyscale-staging.com/api/v2/sessions/ses_gyl6mbksa8xt7b149ib6abld/services?redirect_to=dashboard', python_version='3.8.5', ray_version='2.0.0', ray_commit='cba26cc83f6b5b8a2ff166594a65cb74c0ec8740', address_info={'node_ip_address': '172.31.174.62', 'raylet_ip_address': '172.31.174.62', 'redis_address': None, 'object_store_address': '/tmp/ray/session_2022-12-07_18-49-36_464358_162/sockets/plasma_store', 'raylet_socket_name': '/tmp/ray/session_2022-12-07_18-49-36_464358_162/sockets/raylet', 'webui_url': 'console.anyscale-staging.com/api/v2/sessions/ses_gyl6mbksa8xt7b149ib6abld/services?redirect_to=dashboard', 'session_dir': '/tmp/ray/session_2022-12-07_18-49-36_464358_162', 'metrics_export_port': 57175, 'gcs_address': '172.31.174.62:9031', 'address': '172.31.174.62:9031', 'dashboard_agent_listen_port': 52365, 'node_id': '90ea27f2278480d8d1918562b0d761e272b87b05f92774c3295ea896'})"
- ]
- },
- "execution_count": 2,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
  "source": [
  "import ray\n",
  "\n",

doc/source/ray-air/examples/BUILD

@@ -12,32 +12,12 @@ filegroup(
 # Test all doc/source/ray-air/examples notebooks.
 # --------------------------------------------------------------------
 
-py_test_run_all_notebooks(
- size = "large",
- include = ["*.ipynb"],
- exclude = [
- "huggingface_text_classification.ipynb",
- "torch_detection.ipynb", # Requires GPUs
- "gptj_batch_prediction.ipynb", # Requires GPUs
- "gptj_serving.ipynb", # Requires GPUs
- "stablediffusion_batch_prediction.ipynb", # Requires GPUs
- "gptj_deepspeed_fine_tuning.ipynb", # Requires release test
- "dolly_lightning_fsdp_finetuning.ipynb", # Requires release test
- ],
- data = ["//doc/source/ray-air/examples:air_examples"],
- tags = ["exclusive", "team:ml", "ray_air"],
-)
-
 # GPU Tests
 
 py_test_run_all_notebooks(
  size = "large",
  include = [
- "huggingface_text_classification.ipynb",
- "torch_detection.ipynb",
- "gptj_batch_prediction.ipynb",
  "gptj_serving.ipynb",
- "stablediffusion_batch_prediction.ipynb",
  ],
  exclude = [],
  data = ["//doc/source/ray-air/examples:air_examples"],

doc/source/ray-air/examples/gptj_serving.ipynb

@@ -13,7 +13,7 @@
  "\n",
  "It is highly recommended to read about [Ray Serve Key Concepts](serve-key-concepts) before starting this example.\n",
  "\n",
- "If you are interested in batch prediction (offline inference), see {doc}`/ray-air/examples/gptj_batch_prediction`.\n",
+ "If you are interested in batch prediction (offline inference), see {doc}`/data/examples/gptj_batch_prediction`.\n",
  "\n",
  "```{note}\n",
  "In order to run this example, make sure your Ray cluster has access to at least one GPU with 16 or more GBs of memory. The amount of memory needed will depend on the model.\n",
@@ -75,7 +75,7 @@
  "cell_type": "markdown",
  "metadata": {},
  "source": [
- "Setting up basic serving with Ray Serve is very similar to {doc}`batch inference with Ray Data </ray-air/examples/gptj_batch_prediction>`. First, we define a callable class that will serve as the [Serve deployment](serve-key-concepts-deployment). At runtime, a deployment consists of a number of *replicas*, which are individual copies of the class or function that are started in separate Ray Actors (processes). The number of replicas can be scaled up or down (or even autoscaled) to match the incoming request load.\n",
+ "Setting up basic serving with Ray Serve is very similar to {doc}`batch inference with Ray Data </data/examples/gptj_batch_prediction>`. First, we define a callable class that will serve as the [Serve deployment](serve-key-concepts-deployment). At runtime, a deployment consists of a number of *replicas*, which are individual copies of the class or function that are started in separate Ray Actors (processes). The number of replicas can be scaled up or down (or even autoscaled) to match the incoming request load.\n",
  "\n",
  "We make sure to set the deployment to use 1 GPU by setting `\"num_gpus\"` in `ray_actor_options`. We load the model in `__init__`, which will allow us to save time by initializing a model just once and then use it to handle multiple requests.\n",
  "\n",