Skip to content

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

New pull request New
62 Open 4,949 Closed
62 Open 4,949 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

[CI] Grant id-token to benchmark wheel-build jobs for Sigstore signing
#7911 opened Sep 1, 2026 by quinnlp Contributor • Draft
[DRAFT] investigate fused_moe xeforge kernel
#7910 opened Sep 1, 2026 by quinnlp Contributor • Draft
Unskip test_standard.py::test_sort cases and remove topk patch from pytorch
#7909 opened Sep 1, 2026 by anmyachev Contributor • Draft
Merge OpenAI Triton commit 5889527
#7905 opened Sep 1, 2026 by wdziurdz Contributor Loading…
[TritonIntelGPU] Fix degenerate swizzle patterns for DPAS operands through SLM
#7902 opened Aug 31, 2026 by whitneywhtsang Contributor • Draft
1
10
[Intel] Stop lowering load cg/cs to !nontemporal (#7843) run-benchmarks
#7901 opened Aug 31, 2026 by etiotto Contributor Loading…
1
@etiotto
6
[TritonIntelGPU] Carry batch strides on ttig.2d_block_load (#7882)
#7897 opened Aug 31, 2026 by aditzhaki Loading…
5 tasks done
3
[vLLM] Update vllm pin
#7893 opened Aug 31, 2026 by quinnlp Contributor • Draft
1
[RemoveLayoutConversions] Stop backward slice at while/warp-specialize results run-benchmarks
#7892 opened Aug 31, 2026 by etiotto Contributor Loading…
1
@etiotto
5
[SGLANG] Enable test_fused_moe.py in the MoE suite
#7886 opened Aug 31, 2026 by wdziurdz Contributor Loading…
[SGLANG] Update pin to 771e613d96de0ee89631bc308a2525aaeae9f13e
#7885 opened Aug 31, 2026 by wdziurdz Contributor Loading…
Update PyTorch pin lts run-benchmarks
#7884 opened Aug 31, 2026 by anmyachev Contributor • Draft
[SGLANG] Use tensor descriptors in the fla kernels on the GDN path
#7883 opened Aug 31, 2026 by wdziurdz Contributor Loading…
[CI] Add torchao to nightly builds and local builds
#7879 opened Aug 30, 2026 by aditzhaki • Draft
1
[vLLM] Unskip w8a8_fp8_fused_moe tests
#7877 opened Aug 29, 2026 by anmyachev Contributor Loading…
1
5
[vLLM]
#7874 opened Aug 28, 2026 by quinnlp Contributor • Draft
1
[benchmarks] Run third-party benchmarks on b580 instead of max1550
#7870 opened Aug 28, 2026 by quinnlp Contributor • Draft
Revert "[Windows] Skip test_chain_reduce PTSS scratch-space overflow on a770/xe2"
#7864 opened Aug 27, 2026 by kwasd Contributor • Draft
[Liger] Guard LigerQwen3_5CausalLMOutputWithPast import to fix test c…
#7862 opened Aug 27, 2026 by dev-tomek Contributor • Draft
1
[driver] Serialize load_binary to prevent IGC race condition (#7581)
#7860 opened Aug 27, 2026 by NathanVoldman Contributor • Draft
1
[SGLANG] Fix AWQ test_gemm OOR on B580
#7859 opened Aug 27, 2026 by dev-tomek Contributor • Draft
1
[LoopDistribute] Add an opt-in profitability cost model
#7845 opened Aug 25, 2026 by etiotto Contributor Loading…
@etiotto
1
Switch to C++20 lts
#7839 opened Aug 25, 2026 by anmyachev Contributor • Draft
1
1
[Benchmarks] Update fused_gemm autotune configs
#7836 opened Aug 25, 2026 by JianyuLi01 Loading…
3
[TEST] Add ASan/LeakSanitizer harness and fix memory bugs it found
#7831 opened Aug 24, 2026 by Niz13 Loading…
1
9
ProTip! Follow long discussions with comments:>50.