Weekly GitHub Report for Xla: September 08, 2025 - September 15, 2025 (12:01:31)

Weekly GitHub Report for Xla

Thank you for subscribing to our weekly newsletter! Each week, we deliver a comprehensive summary of your GitHub project's latest activity right to your inbox, including an overview of your project's issues, pull requests, contributors, and commit activity.

---

Table of Contents

• I. News
  • 1.1. Recent Version Releases
  • 1.2. Other Noteworthy Updates
• II. Issues
  • 2.1. Top 5 Active Issues
  • 2.2. Top 5 Stale Issues
  • 2.3. Open Issues
  • 2.4. Closed Issues
  • 2.5. Issue Discussion Insights

• III. Pull Requests
  • 3.1. Open Pull Requests
  • 3.2. Closed Pull Requests
  • 3.3. Pull Request Discussion Insights

• IV. Contributors
  • 4.1. Contributors

I. News

1.1 Recent Version Releases:

No recent version releases were found.

1.2 Version Information:

Please provide the version release information you would like me to analyze and summarize.

II. Issues

2.1 Top 5 Active Issues:

We consider active issues to be issues that that have been commented on most frequently within the last week. Bot comments are omitted.

As of our latest update, there are no active issues with ongoing comments this week.

2.2 Top 5 Stale Issues:

We consider stale issues to be issues that has had no activity within the last 30 days. The team should work together to get these issues resolved and closed as soon as possible.

1. New nvshmem rule breaks the build: This issue reports a build failure caused by a new nvshmem rule introduced in a recent pull request, which leads to an error related to the absence of a getenv method in the repository_ctx object during the CUDA configuration step. The reporter is seeking guidance on whether they need to update their side to resolve this error or if the fix must come from the open_xla project, along with an estimated timeline for addressing the problem.
2. Failed to Parse MLIR generated by Torchax: This issue describes a problem encountered when exporting a PyTorch model to MLIR using the torch-xla torchax export API, where the generated MLIR fails to parse due to an unregistered operation 'vhlo.rsqrt_v2' in the VHLO dialect. The user reports using torch 2.7.0 and torchxla 2.7.0, having built the XLA repository from the corresponding commit, and provides a code snippet along with stablehlo bytecode to help reproduce and diagnose the deserialization failure with StableHLO_v1.9.5.
3. support bazel modules: This issue discusses the potential adoption of Bazel modules within the project, highlighting that Bazel modules have gained significant usage. It specifically points out that XLA is currently the only package in the user's Bazel build that does not support these modules, prompting a request for plans to integrate this feature.
4. Gpu collective performance model bug: This issue addresses a bug in the gpu_collective_performance model where the recent update to lowLatencyBandwidth for AMD links was not applied to the CUDA section, causing failures when using H100 settings. Specifically, the inconsistency in bandwidth configuration leads to errors during model calls, indicating that the CUDA-related parameters need to be updated to match the changes made for AMD links. Since there were fewer than 5 open issues, all of the open issues have been listed above.

2.3 Open Issues

This section lists, groups, and then summarizes issues that were created within the last week in the repository.

Issues Opened This Week: 0

Summarized Issues:

As of our latest update, there are no open issues for the project this week.

2.4 Closed Issues

This section lists, groups, and then summarizes issues that were closed within the last week in the repository. This section also links the associated pull requests if applicable.

Issues Closed This Week: 0

Summarized Issues:

As of our latest update, there were no issues closed in the project this week.

2.5 Issue Discussion Insights

This section will analyze the tone and sentiment of discussions within this project's open and closed issues that occurred within the past week. It aims to identify potentially heated exchanges and to maintain a constructive project environment.

As of our last update, there are no open or closed issues with discussions going on within the past week.

---

III. Pull Requests

3.1 Open Pull Requests

This section provides a summary of pull requests that were opened in the repository over the past week. The top three pull requests with the highest number of commits are highlighted as 'key' pull requests. Other pull requests are grouped based on similar characteristics for easier analysis. Up to 25 pull requests are displayed in this section, while any remaining pull requests beyond this limit are omitted for brevity.

Pull Requests Opened This Week: 8

Key Open Pull Requests

1. Add HNS Rename folder and storage layout API : This pull request adds a new rename folder API for Hierarchical Namespace (HNS) buckets within the existing rename method, introduces a storage layout API to efficiently identify if a bucket is HNS-enabled, and includes unit tests to validate the new rename logic and its fallbacks, thereby enabling a faster, atomic rename operation that improves performance over the previous slow copy-based approach.

• URL: pull/31097

• Merged: No

• Associated Commits: ad593, 5493f, 32c95

2. [XLA:GPU][oneAPI] Enable SPIR-V backend codegen for Intel GPU.: This pull request enables LLVM SPIR-V backend code generation for Intel GPU within the XLA project, laying the groundwork for future updates to support bfloat16 data types despite SPIR-V's lack of native bfloat16 support.

• URL: pull/31116

• Merged: No

• Associated Commits: c2dea, 26b2c

3. Fixed triton_support_test on rocm.: This pull request updates the implementation of IsTritonSupported functions to align with the current Triton implementation for ROCm, fixing the failing triton/support_test unit test on that platform.

• URL: pull/31250

• Merged: No

• Associated Commits: cbf91, 5a00c

Other Open Pull Requests

• ROCm platform enhancements: These pull requests introduce new support and configurations for the ROCm platform, including a ThreadSanitizer configuration for race condition detection and PJRT_Triton_Extension support that enables lowering Pallas Triton calls directly to HSACO. These changes improve hermetic build capabilities and provide ROCm with functionality parallel to CUDA support.
• [pull/31148, pull/31284]

• Bug fix for memory space propagation: This pull request fixes a bug in the PJRT_Client_CreateUninitializedBuffer function by ensuring the memory_space argument is correctly passed to AllocateDestinationBuffer. This correction prevents the argument from defaulting to null and ensures the intended memory space is honored.
• [pull/31292]

• ODR violation fix in function definitions: This pull request resolves an ODR violation caused by duplicate definitions of the xla::cpu::IsSupportedType(...) function by renaming the function in convolution_lib.cc. This approach prevents undefined behavior without requiring widespread changes to the function's multiple invocations.
• [pull/31300]

• HLO support for llama3-8b context parallelism: This pull request adds HLO support for llama3-8b context parallelism using ring attention in the xla/tools/benchmarks/hlo directory. It enables performance tracking of this model through the new benchmark implementation.
• [pull/31108]

3.2 Closed Pull Requests

This section provides a summary of pull requests that were closed in the repository over the past week. The top three pull requests with the highest number of commits are highlighted as 'key' pull requests. Other pull requests are grouped based on similar characteristics for easier analysis. Up to 25 pull requests are displayed in this section, while any remaining pull requests beyond this limit are omitted for brevity.

Pull Requests Closed This Week: 2

Key Closed Pull Requests

1. Fix a shifting issue in scatter determinism expander: This pull request addresses a correctness bug in the scatter_determinism_expander pass by fixing an issue where scatter_set operations with scatter indices containing 0 produced incorrect results due to an improper internal mask caused by prefix scan zero-padding, ensuring the first element of the mask is explicitly set to False to prevent silent data corruption and restore deterministic scatter behavior.

• URL: pull/31063

• Merged: No

• Associated Commits: 8c062

2. Expose num_repeats_with_profiler option to Python HLO Runner interface: This pull request aims to expose the num_repeats_with_profiler option to the Python HLO Runner interface, enabling profiling with more than one iteration, which was previously missed in an earlier pull request.

• URL: pull/31074

• Merged: No

• Associated Commits: 8960d

3.3 Pull Request Discussion Insights

This section will analyze the tone and sentiment of discussions within this project's open and closed pull requests that occurred within the past week. It aims to identify potentially heated exchanges and to maintain a constructive project environment.

Based on our analysis, there are no instances of toxic discussions in the project's open or closed pull requests from the past week.

---

IV. Contributors

4.1 Contributors

Active Contributors:

We consider an active contributor in this project to be any contributor who has made at least 1 commit, opened at least 1 issue, created at least 1 pull request, or made more than 2 comments in the last month.

If there are more than 10 active contributors, the list is truncated to the top 10 based on contribution metrics for better clarity.

Contributor	Commits	Pull Requests	Issues	Comments
shawnwang18	22	1	0	1
othakkar	12	3	0	7
athurdekoos	12	1	0	0
sergachev	10	2	0	0
mraunak	10	1	0	0
sergey-kozub	6	2	0	0
penpornk	1	0	0	7
mgoldfarb-nvidia	7	1	0	0
bhavani-subramanian	4	1	0	0
sfvaroglu	3	2	0	0