Skip to content

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

New pull request New
39 Open 4,288 Closed
39 Open 4,288 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

[NFI] Move getOpIdx, getDpasLayout, computeTransposeShuffleMapping to BlockIOUtils
#6806 opened May 1, 2026 by whitneywhtsang Contributor Loading…
[NFI] Move vBlocks capping into getBlockIOTileSize<true>
#6805 opened May 1, 2026 by whitneywhtsang Contributor Loading…
[TritonIntelGPU] Add Subgroup2DBlockLoadOpConversion for ttig.2d_block_load
#6804 opened May 1, 2026 by whitneywhtsang Contributor Loading…
[vLLM] Update pin to 9f771b3ab92d26a7d91a8255572c5d8d2b3ad601
#6803 opened Apr 30, 2026 by quinnlp Contributor • Draft
[TritonIntelGPU] Add LowerTo2DBlockLoad pass for descriptor loads
#6801 opened Apr 30, 2026 by whitneywhtsang Contributor Loading…
7
[RemoveMasks] Accept sle/ult/ule predicates and compound arith.andi masks run-benchmarks
#6796 opened Apr 30, 2026 by etiotto Contributor Loading…
1
@etiotto
3
[GPUToTritonGEN] Handle Constant address space in memory space conversion
#6795 opened Apr 30, 2026 by whitneywhtsang Contributor Loading…
2 tasks done
[VLLM][Benchmarks] Reduce peak memory in unified_attention benchmark
#6794 opened Apr 30, 2026 by dev-tomek Contributor Loading…
2
9
Merge OpenAI Triton commit e570a63
#6793 opened Apr 30, 2026 by wdziurdz Contributor Loading…
2
[SGLANG] [Benchmarks] Initial integration of sglang kernels to benchmarks
#6789 opened Apr 30, 2026 by chengjunlu Contributor Loading…
1
18
Widen tt.load too; rename pass to WidenLoadStoreEncoding
#6787 opened Apr 29, 2026 by etiotto Contributor Loading…
@etiotto
3
Quinnlp/pin update artur
#6784 opened Apr 29, 2026 by quinnlp Contributor • Draft
Unskip test_core.py::test_noinline[shared] test since it's already fixed in agama 1222
#6783 opened Apr 29, 2026 by anmyachev Contributor Loading…
1
3
[LoadStoreOpToLLVM] Honor eviction_policy hints via LSC cache modes run-benchmarks
#6775 opened Apr 27, 2026 by etiotto Contributor Loading…
1
@etiotto
8
Migrate benchmark workflows to triton-benchmarks CLI (#6113) run-benchmarks
#6766 opened Apr 27, 2026 by januszjah Contributor Loading…
15
[DRAFT] Update Triton benchmark attention kernel to SYCL-TLA 0.8 version run-benchmarks
#6765 opened Apr 27, 2026 by chengjunlu Contributor • Draft
[TritonIntelGPU] Add ttig.2d_block_load op to separate 2D block IO decision from LLVM lowering run-benchmarks
#6762 opened Apr 25, 2026 by whitneywhtsang Contributor • Draft
10
[vLLM] update pin to f768b4473e1bd55023dcaff63984cfdd08902fc8
#6758 opened Apr 24, 2026 by quinnlp Contributor • Draft
1
8
Revert "[vLLM][SKIPLIST] Skip failing mamba tests (tracked by #6713) (#6716)"
#6732 opened Apr 21, 2026 by quinnlp Contributor • Draft
1
[UTILS] Aggregation level option
#6710 opened Apr 20, 2026 by slawblauciak Contributor Loading…
1
16
[PROTON] Enable tensor metrics API for XPU (#5727)
#6709 opened Apr 20, 2026 by wdziurdz Contributor • Draft
1
@wdziurdz
Move set_fast_math pass after llvm.link_extern_libs
#6685 opened Apr 16, 2026 by anmyachev Contributor • Draft
3
[CRI] Add ScalarizePtrVectorsPass to eliminate pointer vectors before SPIR-V
#6581 opened Apr 7, 2026 by wdziurdz Contributor • Draft
1
@wdziurdz
6
[DRAFT][VLLM] fused_moe_kernel
#6536 opened Apr 1, 2026 by chengjunlu Contributor • Draft
[SYCL][XPU] Use SYCL work group scratch memory extension lts run-benchmarks
#6512 opened Mar 30, 2026 by uditagarwal97 Contributor • Draft
@uditagarwal97
9
ProTip! Follow long discussions with comments:>50.