Skip to content

Pull requests: openxla/xla

New pull request New
466 Open 33,879 Closed
466 Open 33,879 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[XLA:GPU] split dimensions greedly including ones in
#34946 opened Dec 7, 2025 by copybara-service bot Loading…
@metaflow
[ROCm] Add support for parametrized rocm hermetic dependency
#34945 opened Dec 7, 2025 by alekstheod • Draft
[Autotuner] Fix behavior when cublas is disabled and autotune level is set to 0.
#34944 opened Dec 7, 2025 by copybara-service bot Loading…
[ROCM] Fix rocm build on cross compile / non hermetic setups
#34943 opened Dec 7, 2025 by copybara-service bot Loading…
@wsmoses
Automated Code Change
#34942 opened Dec 7, 2025 by copybara-service bot Loading…
Gracefully handle missing parameter/output shardings from single-device atom executables
#34941 opened Dec 6, 2025 by copybara-service bot Loading…
Optimize remap ops in IFRT IR by performing more work at compile time
#34939 opened Dec 6, 2025 by copybara-service bot Loading…
internal change only
#34934 opened Dec 6, 2025 by copybara-service bot Loading…
Fix use-after-free in PjRtCApiClient
#34933 opened Dec 6, 2025 by copybara-service bot Loading…
@hhb
Only show warning about nvml symbol when relevant
#34932 opened Dec 6, 2025 by copybara-service bot Loading…
@ermilovmaxim
Automated Code Change
#34930 opened Dec 6, 2025 by copybara-service bot Loading…
Automated Code Change
#34928 opened Dec 6, 2025 by copybara-service bot Loading…
Generalize CommonPjRtClient::PrepareArguments for processing all the input
#34927 opened Dec 6, 2025 by copybara-service bot Loading…
Implement a new two-stage ProgramInterpreter design for better efficiency and safety
#34926 opened Dec 6, 2025 by copybara-service bot Loading…
[XLA] Print backend config in HloPrintOptions::ShortParsable()
#34925 opened Dec 6, 2025 by copybara-service bot Loading…
@mkuperst
Change OpSourceInfo::source_file from absl::string_view to std::string
#34924 opened Dec 6, 2025 by copybara-service bot Loading…
@zzzaries
[xla:codegen] excise GPU deps out of "passes" target
#34923 opened Dec 6, 2025 by copybara-service bot Loading…
@cota
[XLA:Original Value] Propagate OriginalValue in WhileLoopSimplifier when removing constant loop-carried values.
#34921 opened Dec 5, 2025 by copybara-service bot Loading…
Integrate LLVM at llvm/llvm-project@29fa151a0772
#34919 opened Dec 5, 2025 by copybara-service bot Loading…
Add support for watched sync flag filtering
#34918 opened Dec 5, 2025 by copybara-service bot Loading…
@Matt-Hurd
Turn on the scatter determinism expander by default
#34917 opened Dec 5, 2025 by serach24 Loading…
[XLA:CPU] Link Eigen IR module into XLA JITted code. Attempt 3.
#34916 opened Dec 5, 2025 by copybara-service bot Loading…
@seantalts
[XLA:GPU] Fix Cublaslt fp8 to dummy nullptr c pointer when beta = 0
#34912 opened Dec 5, 2025 by Cjkkkk Loading…
1
PR #34704: [GPU] Fix mixed inputs F8 dot in Triton codegen.
#34910 opened Dec 5, 2025 by copybara-service bot Loading…
Extend the parser and the verifier to support the use of buffer types in asynchronous custom-calls.
#34908 opened Dec 5, 2025 by copybara-service bot Loading…
@bixia1
ProTip! no:milestone will show everything without a milestone.