🔄 daily merge: master → main 2025-11-03 #668
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…Autoscaling config (ray-project#57260) In KubeRay v1.5, new structured `Resources` and `Labels` fields will be added to both the `HeadGroupSpec` and `WorkerGroupSpec` to enable users to explicitly define these values without relying on `rayStartParams`. This support is implemented in ray-project/kuberay#4106. In order for this change to work with the Ray autoscaler, this PR adds support for checking the `resources` and `labels` field (with precedence over the values `rayStartParams` and k8s constainer spec) and generating the resulting autoscaling config. This change is compatible with older versions of KubeRay that do not have these new fields, since we fall back to the previous logic when the top-level fields aren't specified. Example: For a group spec specified like this: ``` workerGroupSpecs: - groupName: worker-group-1 replicas: 1 resources: GPU: 8 CPU: 16 labels: ray.io/zone: us-west2-a ray.io/region: us-west2 ``` The resulting autoscaling config for worker-group-1 would be: ``` "worker-group-1": { "labels": {" ray.io/zone": "us-west2-a", " ray.io/region": "us-west2"}, ... "resources": { "CPU": 16, GPU: 8, }, }, ``` ## Related issue number Contributes to ray-project#51564 --------- Signed-off-by: Ryan O'Leary <[email protected]>
…ing cluster teardown (ray-project#57610) After running `ray down` several resources (a managed service identiy, network security group, etc) at left in the subscription and re-running `ray up` (without specifying --no-config-cache) will sometimes run into errors because of this. ## Related issue number Fixes: ray-project#55392 Signed-off-by: Mark Rossett <[email protected]>
The old expression evaluator did not correctly handle `is_in` which failed tests in `test_expression_evaluator` ## Related issues Fixes ray-project#57820 --------- Signed-off-by: Goutam <[email protected]>
Release tests, unit tests, doctests, and examples are all migrated to V2, so this PR turns V2 on by default. To run with Train V1 (deprecated), set `RAY_TRAIN_V2_ENABLED=0`. --------- Signed-off-by: Justin Yu <[email protected]>
…ct#57133) This PR adds a workspace template that walks users through how to integrate PyTorch Profiler with Ray Train. The purpose of this template is to walk user through how to generate trace/memory profile with Pytorch Profiler in the TorchTrainer. For a high level overview, this template covers: 1. A hands-on example of training an image classification model 2. A simple torch profiler integration script 3. Some more advanced use cases including `record_function` to customize the profiling experience. 4. a successful release test run: https://buildkite.com/ray-project/release/builds/63492#0199e3e4-fa8c-4f4f-a92c-f6d47a415c53 Testing: testing in Anyscale workspace --------- Signed-off-by: Lehui Liu <[email protected]>
Signed-off-by: abrar <[email protected]>
…uides and improved navigation (ray-project#57787) Signed-off-by: Kourosh Hakhamaneshi <[email protected]> Signed-off-by: kourosh hakhamaneshi <[email protected]> Co-authored-by: angelinalg <[email protected]>
…ss/postprocess (ray-project#57826) Signed-off-by: Nikhil Ghosh <[email protected]>
## Description This removes an orphaned code file that was previously used by the Preprocessor User Guide. ## Related issues Corresponding User Guide was removed in ray-project#44006. Closes ray-project#57867. ## Additional details This test started failing because of the new `XGBoostTrainer` API enabled by default with Ray Train V2. Rather than update the snippet, removing this code instead. Signed-off-by: Matthew Deng <[email protected]>
adding eslint and prettier script to precommit before getting rid of format.sh 1 step closer to replacing scripts/format.sh with pre-commit (pre-commit is currently missing eslint) tested locally: <img width="898" height="929" alt="image" src="https://github.com/user-attachments/assets/58c77fb7-bdde-47ae-ac2b-b864334b3f30" /> --------- Signed-off-by: elliot-barn <[email protected]>
First test running on AKS cloud! --------- Signed-off-by: kevin <[email protected]> Signed-off-by: Kevin H. Luu <[email protected]> Co-authored-by: Lonnie Liu <[email protected]>
## Description Updating so that the module shows as `ray.train` rather than `ray.train.v2.api.exceptions` ## Testing https://anyscale-ray--57865.com.readthedocs.build/en/57865/train/api/doc/ray.train.v2.api.data_parallel_trainer.DataParallelTrainer.fit.html#ray.train.v2.api.data_parallel_trainer.DataParallelTrainer.fit <img width="960" height="302" alt="image" src="https://github.com/user-attachments/assets/02206542-54fe-4674-b2b4-1868fa7e8580" /> Signed-off-by: Matthew Deng <[email protected]>
- Add 2 hello world tests with regular base image & custom image running on GCE --------- Signed-off-by: kevin <[email protected]> Signed-off-by: Kevin H. Luu <[email protected]>
## Description Bump from small to medium due to timeouts happening specifically in py3.12 tests. --------- Signed-off-by: Matthew Deng <[email protected]>
## Why are these changes needed? Computing the `num_module_steps_trained_(lifetime)_throughput` metrics are biased due to the way how we record throughput times in a loop over module batches. This PR offers a fix to this bias. ## Related issue number <!-- For example: "Closes ray-project#1234" --> ## Checks - [x] I've signed off every commit(by using the -s flag, i.e., `git commit -s`) in this PR. - [x] I've run pre-commit jobs to lint the changes in this PR. ([pre-commit setup](https://docs.ray.io/en/latest/ray-contribute/getting-involved.html#lint-and-formatting)) - [x] I've included any doc changes needed for https://docs.ray.io/en/master/. - [ ] I've added any new APIs to the API Reference. For example, if I added a method in Tune, I've added it in `doc/source/tune/api/` under the corresponding `.rst` file. - [x] I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/ - Testing Strategy - [x] Unit tests - [ ] Release tests - [ ] This PR is not tested :( --------- Signed-off-by: simonsays1980 <[email protected]> Co-authored-by: Kamil Kaczmarek <[email protected]>
…orker` (ray-project#57859) ## Description The type annotation for `actor_location_tracker` is currently `ActorLocationTracker`, but it should be `ray.actor.ActorHandle[ActorLocationTracker]`. This PR fixes that issue. Signed-off-by: Balaji Veeramani <[email protected]>
ray-project#57834) Signed-off-by: Jiajun Yao <[email protected]>
…r'. (ray-project#57673) <!-- Thank you for your contribution! Please review https://github.com/ray-project/ray/blob/master/CONTRIBUTING.rst before opening a pull request. --> <!-- Please add a reviewer to the assignee section when you create a PR. If you don't have the access to it, we will shortly find a reviewer and assign them to your PR. --> ## Why are these changes needed? The type hints for `learner_connector` in `AlgorithmConfig.training` was deprecated still using the `RLModule` as parameter. This PR adjust type hints to the actual expected form of the callable. ## Related issue number <!-- For example: "Closes ray-project#1234" --> ## Checks - [x] I've signed off every commit(by using the -s flag, i.e., `git commit -s`) in this PR. - [x] I've run pre-commit jobs to lint the changes in this PR. ([pre-commit setup](https://docs.ray.io/en/latest/ray-contribute/getting-involved.html#lint-and-formatting)) - [x] I've included any doc changes needed for https://docs.ray.io/en/master/. - [ ] I've added any new APIs to the API Reference. For example, if I added a method in Tune, I've added it in `doc/source/tune/api/` under the corresponding `.rst` file. - [x] I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/ - Testing Strategy - [ ] Unit tests - [ ] Release tests - [ ] This PR is not tested :( Signed-off-by: simonsays1980 <[email protected]>
`result_of_t` is deprecated Signed-off-by: Lonnie Liu <[email protected]>
…ectural Design (ray-project#57889) Signed-off-by: Kourosh Hakhamaneshi <[email protected]>
- disables java tests; ray java not supported on apple silicon yet. - skipping cpp tests that are not passing yet we already stopped releasing macos wheels for Intel silicon, the tests that are disabled or skipped were never passing on apple silicon, so nothing is regressed. Signed-off-by: Lonnie Liu <[email protected]>
…ay-project#57876) ## Description ## Related issues Closes ray-project#57847 ## Additional information Signed-off-by: daiping8 <[email protected]>
…ystem cgroup (ray-project#57864) For more details about the resource isolation project see ray-project#54703. When starting the head node, move the dashboard api server's subprocesses into the system cgroup. I updated the integration test and added a helpful error message because the test will break in the future when a new dashboard module is added. I ran the integration tests 25 times locally. > (ray2) ubuntu@devbox:~/code/ray2$ python -m pytest -s python/ray/tests/resource_isolation/test_resource_isolation_integration.py --count 25 -x ... collecting ... python/ray/tests/resource_isolation/test_resource_isolation_integration.py ✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓ 25% ██▌ 2025-10-17 23:13:51,897 INFO worker.py:1833 -- Connecting to existing Ray cluster at address: 172.31.12.251:6379... 2025-10-17 23:13:51,905 INFO worker.py:2004 -- Connected to Ray cluster. View the dashboard at http://127.0.0.1:8265 python/ray/tests/resource_isolation/test_resource_isolation_integration.py ✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓ 26% ██▋ 2025-10-17 23:13:57,592 INFO worker.py:1833 -- Connecting to existing Ray cluster at address: 172.31.12.251:6379... 2025-10-17 23:13:57,598 INFO worker.py:2004 -- Connected to Ray cluster. View the dashboard at http://127.0.0.1:8265 python/ray/tests/resource_isolation/test_resource_isolation_integration.py ✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓ 98% █████████▊2025-10-17 23:19:45,417 INFO worker.py:2004 -- Started a local Ray instance. View the dashboard at http://127.0.0.1:8265 python/ray/tests/resource_isolation/test_resource_isolation_integration.py ✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓ 99% █████████▉2025-10-17 23:19:50,194 INFO worker.py:2004 -- Started a local Ray instance. View the dashboard at http://127.0.0.1:8265 python/ray/tests/resource_isolation/test_resource_isolation_integration.py ✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓✓ 100% ██████████ Results (366.41s): 100 passed --------- Signed-off-by: irabbani <[email protected]>
…roject#57037) During the execution of tail_job_logs() after the job submission, if the ray head connection breaks, the tail_job_logs() will not raise any error. The error should be raised. Query the rayjob status when receiving the message, and raise error if connection closed with rayjob not in terminate stage. ## Related issue number Closes: ray-project#57002 --------- Signed-off-by: machichima <[email protected]>
…ay-project#57802) ## Description 1. This PR added the `jax.distributed.shutdown()` for JaxBackend in order to free up any leaked resources on TPU RayTrainWorkers. 2. if `jax.distributed` is not on, it is a noop: https://docs.jax.dev/en/latest/_autosummary/jax.distributed.shutdown.html 3. Tested on Anyscale workspace. <img width="1264" height="62" alt="image" src="https://github.com/user-attachments/assets/f28102ff-f6d1-4da0-b41a-6cc785603e72" />
…ay Serve LLM (ray-project#57830) Signed-off-by: Kourosh Hakhamaneshi <[email protected]>
we are not releasing `x86_64` wheels anymore Signed-off-by: Lonnie Liu <[email protected]>
…57817) Signed-off-by: dayshah <[email protected]>
…igurable (ray-project#57705) Recently, when we ran performance tests with task event generation turned on. We saw some performance regression when the workloads ran on very small CPU machines. With further investigation, the overhead mainly comes from the name format convention when converting the proto message to JSON format payload in the aggregator agent. This PR adds an env var for the config to control the name conversion behavior and update the corresponding tests. Also note that, eventually we are planning to remove this config turn off the field name conversion by default after migrated all the current event usage. --------- Signed-off-by: Mengjin Yan <[email protected]>
## Description Adds PredicatePushdown Rule to Ray Data. Pushes predicates through Read (for supporting datasources), Union ## Related issues > Link related issues: "Fixes ray-project#1234", "Closes ray-project#1234", or "Related to ray-project#1234". ## Additional information > Optional: Add implementation details, API changes, usage examples, screenshots, etc. --------- Signed-off-by: Goutam <[email protected]>
Signed-off-by: abrar <[email protected]>
…ct#58281) Supports token based authentication in dashboard head sdk, all clients which build on top of the submission_client will now support token auth out of the box. so this covers all cli commands like job submit, state api, serve related cli commands etc. --------- Signed-off-by: sampan <[email protected]> Signed-off-by: Sampan S Nayak <[email protected]> Signed-off-by: Edward Oakes <[email protected]> Co-authored-by: sampan <[email protected]> Co-authored-by: Edward Oakes <[email protected]>
this helps prevent an edge case when using file based log exporters like vector that use fingerprinting [ref](https://vector.dev/docs/reference/configuration/sources/file/#fingerprint) to identify unique files. example edge case that this fixes: two jobs are submitted to a cluster and begin executing at the same time, they both contain an invalid entrypoint that references a nonexistant file before fix: - both jobs have the identical "Runtime env is setting up" log with identical timestamps - both jobs have identical entrypoint failure logs as a result, the log files for these jobs are identical, so vector will only export one. after fix: - both jobs have the identical "Runtime env is setting up" log with identical timestamps - each job has a **unique** entrypoint log containing its job_id - both jobs have identical entrypoint failure logs vector can differentiate between these two files, so both will be exported --------- Signed-off-by: Chris Fellowes <[email protected]> Signed-off-by: chrisfellowes <[email protected]> Signed-off-by: Edward Oakes <[email protected]> Co-authored-by: Edward Oakes <[email protected]>
…8341) When running on older machines with less impressive CPU, and when under a bit of load. We've seen the dashboard failing to start in the expected 200 iterations (`sleep(0.1)` for 20 seconds). Increases this timeout to 60 seconds. --------- Signed-off-by: morotti <[email protected]> Signed-off-by: Edward Oakes <[email protected]> Co-authored-by: Edward Oakes <[email protected]>
…s-process support (ray-project#58332) Signed-off-by: Kourosh Hakhamaneshi <[email protected]>
…oject#58344) so that we can perform surgeries in the last minute if required. Signed-off-by: Lonnie Liu <[email protected]>
add `--use-pep517` flag; otherwise some part of the wheel building logic does not work on windows python 3.12 also removes the unnecessary "uninstall+reinstall" dance. the script only builds the wheel, it does not (and should not) install the wheel. Signed-off-by: Lonnie Liu <[email protected]>
observability release tests on py3.10 Successful release test run: https://buildkite.com/ray-project/release/builds/65851 failing tests are set to manual (disabled): aws_cluster_launcher_release_image k8s_serve_ha_test enabling agent_stress_test.gce which is now passing --------- Signed-off-by: elliot-barn <[email protected]>
## Description Replace `map_batches` and numpy invocations with `with_column` and arrow kernels Release test: https://buildkite.com/ray-project/release/builds/66243#019a37da-4d9d-4f19-9180-e3f3dc3f8043 ## Related issues > Link related issues: "Fixes ray-project#1234", "Closes ray-project#1234", or "Related to ray-project#1234". ## Additional information > Optional: Add implementation details, API changes, usage examples, screenshots, etc. --------- Signed-off-by: Goutam <[email protected]>
…collate_fn (ray-project#58327) Signed-off-by: Gang Zhao <[email protected]> Co-authored-by: Gang Zhao <[email protected]>
## Description This fixes the symmetric-run cli workflow. Right now if you use `ray symmetric-run` on 2.51 like ``` ray symmetric-run --address 127.0.0.1:6379 -- python my_script.py ``` it will throw since the `symmetric-run` arg is not caught. This was only caught once it became part of the CLI. ## Related issues ## Additional information > Optional: Add implementation details, API changes, usage examples, screenshots, etc. --------- Signed-off-by: Richard Liaw <[email protected]>
…t#58247) Updating hello world release & cluster release tests to run on py3.10 Passing release tests: https://buildkite.com/ray-project/release/builds/65844 --------- Signed-off-by: elliot-barn <[email protected]>
Fix typos Signed-off-by: Jiajun Yao <[email protected]>
The current examples describe that label bundles are written as:
`[{"ray.io/accelerator-type": "H100"}* 2]`, i.e. a dict * integer.
This is wrong it has to be the list that is multiplied.
This PR fixes this.
Signed-off-by: Daraan <[email protected]>
## Description In this function, `Result::from_path` is implemented in ray train v2, which reconstructs a `Result` object from the checkpoints. This implementation leverages `CheckpointManager` and refers to https://github.com/ray-project/ray/blob/master/python/ray/train/v2/_internal/execution/controller/controller.py#L512-L540 --------- Signed-off-by: xgui <[email protected]> Signed-off-by: Justin Yu <[email protected]> Co-authored-by: Justin Yu <[email protected]>
Add "WORKDIR /home/ray" in build-docker.sh. If "WORKDIR" is not set, it defaults to /root, causing permission issues with conda init. ``` 31.00 # >>>>>>>>>>>>>>>>>>>>>> ERROR REPORT <<<<<<<<<<<<<<<<<<<<<< 31.00 31.00 Traceback (most recent call last): 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/conda/exception_handler.py", line 18, in __call__ 31.00 return func(*args, **kwargs) 31.00 ^^^^^^^^^^^^^^^^^^^^^ 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/conda/cli/main.py", line 44, in main_subshell 31.00 context.__init__(argparse_args=pre_args) 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/conda/base/context.py", line 517, in __init__ 31.00 self._set_search_path( 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/conda/common/configuration.py", line 1430, in _set_search_path 31.00 self._search_path = IndexedSet(self._expand_search_path(search_path, **kwargs)) 31.00 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/boltons/setutils.py", line 118, in __init__ 31.00 self.update(other) 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/boltons/setutils.py", line 351, in update 31.00 for o in other: 31.00 ^^^^^ 31.00 File "/home/ray/anaconda3/lib/python3.12/site-packages/conda/common/configuration.py", line 1403, in _expand_search_path 31.00 if path.is_file() and ( 31.00 ^^^^^^^^^^^^^^ 31.00 File "/home/ray/anaconda3/lib/python3.12/pathlib.py", line 892, in is_file 31.00 return S_ISREG(self.stat().st_mode) 31.00 ^^^^^^^^^^^ 31.00 File "/home/ray/anaconda3/lib/python3.12/pathlib.py", line 840, in stat 31.00 return os.stat(self, follow_symlinks=follow_symlinks) 31.00 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 31.00 PermissionError: [Errno 13] Permission denied: '$XDG_CONFIG_HOME/conda/.condarc' 31.00 31.00 `$ /home/ray/anaconda3/bin/conda init` 31.00 31.00 environment variables: 31.00 CIO_TEST=<not set> 31.00 CONDA_ROOT=/home/ray/anaconda3 31.00 CURL_CA_BUNDLE=<not set> 31.00 HTTPS_PROXY=<set> 31.00 HTTP_PROXY=<set> 31.00 LD_LIBRARY_PATH=:/usr/local/nvidia/lib64 31.00 LD_PRELOAD=<not set> 31.00 NO_PROXY=<set> 31.00 PATH=/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/ 31.00 bin:/sbin:/bin:/usr/local/nvidia/bin 31.00 PYTHON_VERSION=3.9 31.00 REQUESTS_CA_BUNDLE=<not set> 31.00 SSL_CERT_FILE=<not set> 31.00 http_proxy=<set> 31.00 https_proxy=<set> 31.00 no_proxy=<set> ``` Signed-off-by: my-vegetable-has-exploded <[email protected]> Co-authored-by: Edward Oakes <[email protected]>
…ct#58320) Signed-off-by: win5923 <[email protected]>
…oject#58329) Created by release automation bot. Update with commit a69004e Signed-off-by: kevin <[email protected]>
… and GRPO. (ray-project#57961) ## Description Example for first blog in the RDT series using NIXL for GPU-GPU tensor transfers. --------- Signed-off-by: Ricardo Decal <[email protected]> Signed-off-by: Stephanie Wang <[email protected]> Co-authored-by: Ricardo Decal <[email protected]> Co-authored-by: Stephanie Wang <[email protected]> Co-authored-by: Qiaolin Yu <[email protected]>
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
The pull request #668 has too many files changed.
The GitHub API will only let us fetch up to 300 changed files, and this pull request has 5194.
Summary of ChangesHello @antfin-oss, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request represents an automated daily merge from the Highlights
Ignored Files
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request is an automated daily merge that includes a massive set of changes, primarily focused on refactoring the CI/CD pipelines and Bazel build system. The changes are extensive and touch many configuration files, build scripts, and some parts of the core C++ and Python code.
Key changes include:
- CI/CD Refactoring: The Buildkite pipelines have been significantly modularized. Image building steps are separated, and dependency management is centralized with a new
raydepsetssystem. This should improve maintainability and clarity of the CI configuration. - Bazel Build System Overhaul: The root
BUILD.bazelfile has been cleaned up, with targets moved to more appropriate subdirectories. The packaging logic has been modernized usingrules_pkginstead of customgenrules. The workspace name has been updated toio_ray. - Code Quality and Linting: Pre-commit hooks have been updated and expanded, with tools like
semgrep,vale, andeslintbeing added. The oldformat.shscript has been removed in favor ofpre-commit. - Dependency Management: Switched from Miniconda to Miniforge. Several dependencies have been updated or patched.
- Platform Support: macOS builds for x86_64 seem to have been removed, standardizing on arm64 for macOS. Java tests on macOS also appear to be disabled.
- Code Modernization: Some C++ code has been updated to use modern C++ features (e.g.,
std::invoke_result_t).
The overall direction of these changes is very positive, leading to a more maintainable, reproducible, and robust build and test system.
I've found a couple of issues in the test suite where assertions seem to be incorrect after the refactoring of how Docker image tags are generated. These tests will likely fail and need to be updated. My review comments point these out with suggestions for fixes.
| with mock.patch("subprocess.check_call", side_effect=_mock_subprocess): | ||
| LinuxTesterContainer("team", build_type="debug") | ||
| docker_image = f"{_DOCKER_ECR_REPO}:{_RAYCI_BUILD_ID}-team" | ||
| docker_image = f"{_DOCKER_ECR_REPO}:team" |
There was a problem hiding this comment.
The docker_image variable is constructed without the RAYCI_BUILD_ID prefix, but the _get_docker_image method, which is called by LinuxTesterContainer's install_ray method, will prepend it. This will cause the assertion on the next line to fail. The RAYCI_BUILD_ID is set to "a1b2c3d4" in the test setup.
Suggested change
| docker_image = f"{_DOCKER_ECR_REPO}:team" | |
| docker_image = f"{_DOCKER_ECR_REPO}:a1b2c3d4-team" |
| image = ( | ||
| "029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp:unknown-hi" | ||
| ) | ||
| image = "029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp:hi" |
There was a problem hiding this comment.
The image variable is constructed without the RAYCI_BUILD_ID prefix, but the _get_docker_image method, which is called by WindowsContainer's install_ray method, will prepend it. This will cause the assertion on the next line to fail. The RAYCI_BUILD_ID is set to "a1b2c3d4" in the test setup.
image = (
"029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp:a1b2c3d4-hi"
)
|
This pull request has been automatically marked as stale because it has not had You can always ask for help on our discussion forum or Ray's public slack channel. If you'd like to keep this open, just leave any comment, and the stale label will be removed. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This Pull Request was created automatically to merge the latest changes from
masterintomainbranch.📅 Created: 2025-11-03
🔀 Merge direction:
master→main🤖 Triggered by: Scheduled
Please review and merge if everything looks good.