Skip to content

Pull requests: intel/intel-xpu-backend-for-triton

New pull request New
34 Open 3,565 Closed
34 Open 3,565 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

Merge OpenAI Triton commit 343052b
#5720 opened Dec 19, 2025 by whitneywhtsang • Draft
[VLLM][unfied attention] Use 2d load for Q matrix when possible
#5713 opened Dec 18, 2025 by Egor-Krivov Loading…
1
[DEBUG] Reland Proton change
#5712 opened Dec 18, 2025 by anmyachev • Draft
Workaround on seg fault clReleaseGlSharedEventINTEL
#5711 opened Dec 18, 2025 by wdziurdz Loading…
3
Enables sub-group-size=32 for kernel using DPAS operations.
#5709 opened Dec 18, 2025 by chengjunlu • Draft
4
[LoadStoreOpToLLVM] Support load columns major matrix for more cases
#5708 opened Dec 18, 2025 by chengjunlu • Draft
[WIP]: Range Analysis
#5705 opened Dec 17, 2025 by etiotto • Draft
@etiotto
6
[VLLM] Change grid for MOE kernel
#5703 opened Dec 17, 2025 by Egor-Krivov Loading…
1
2
Bump actions/download-artifact from 6 to 7 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#5660 opened Dec 15, 2025 by dependabot bot Loading…
Bump actions/cache from 4 to 5 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#5659 opened Dec 15, 2025 by dependabot bot Loading…
Bump actions/upload-artifact from 5 to 6 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#5658 opened Dec 15, 2025 by dependabot bot Loading…
[VLLM] Update vllm pin
#5656 opened Dec 15, 2025 by Egor-Krivov Loading…
3 of 4 tasks
1
5
[Build and test] Disable ignore errors on windows
#5655 opened Dec 15, 2025 by dev-tomek • Draft
1
[LoadStoreOpToLLVM] Enable block io for all layout by default.
#5641 opened Dec 11, 2025 by chengjunlu Loading…
1
[DEBUG] Try most recent PTI version
#5635 opened Dec 10, 2025 by anmyachev • Draft
1
[intel] specialized kernels
#5620 opened Dec 8, 2025 by januszjah • Draft
1
Enable Proton for python/tutorials/09-persistent-matmul.py
#5601 opened Dec 3, 2025 by anmyachev • Draft
Prevent generation of 1-element vectors
#5599 opened Dec 2, 2025 by MrSidims • Draft
[Gluon] Support tensor descriptors and explicit load/store/prefetch operations
#5586 opened Dec 1, 2025 by mieshkiwrk Loading…
@mieshkiwrk
28
Reenable hanging gluon test after driver update
#5562 opened Nov 27, 2025 by HBN-MichalSzy • Draft
1
[DEBUG] Try to run Proton tests on windows
#5542 opened Nov 24, 2025 by anmyachev • Draft
use pytest-skip plugin for selection in the test script
#5502 opened Nov 18, 2025 by slawblauciak Loading…
1
6
[LoadStoreOpToLLVM] Unify the 2D block IO lowering code for both regular pointer and block pointer
#5500 opened Nov 18, 2025 by chengjunlu Loading…
1
17
Add one autotuning config to the flex attention benchmark
#5303 opened Oct 14, 2025 by admitric • Draft
8
[RemoveLayoutConversions]: Failure to compile loop yielding result consumed by reduce operation
#5262 opened Oct 6, 2025 by etiotto • Draft
@etiotto
ProTip! Exclude everything labeled bug with -label:bug.