Skip to content

Pull requests: iree-org/iree

New pull request New
224 Open 18,744 Closed
224 Open 18,744 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

[HAL][LocalTask] Add task_topology_group_count device creation parameter
#24260 opened Apr 24, 2026 by hanhanW Contributor Loading…
1
[CI][TorchModels] Relax mi325 golden for flaky llama_8b_fp8 prefill_seq2048_data_tiling benchmark
#24257 opened Apr 24, 2026 by hanhanW Contributor Loading…
2
[Codegen][DMA] Skip untuned XOR swizzle fallback for BF16
#24254 opened Apr 24, 2026 by Yu-Zhewen Contributor Loading…
[HAL/CPU] Local Runtime Rewrite hal/cpu Runtime Host/CPU-based HAL backend
#24248 opened Apr 24, 2026 by benvanik Collaborator Loading…
[ROCDL] Add pass to group buffer loads for better instruction scheduling
#24247 opened Apr 24, 2026 by Max191 Contributor • Draft
[Codegen] Duplicate operations in tile size analysis
#24246 opened Apr 24, 2026 by sommerlukas Contributor Loading…
[LinalgExt] Refactor IGEMM detail computation and update layout decisions
#24245 opened Apr 24, 2026 by Max191 Contributor Loading…
1
[Codegen] Improve constant handling in VectorLayoutAnalysis
#24243 opened Apr 24, 2026 by sommerlukas Contributor Loading…
1
[Codegen][DMA] Fix OOB clamping for subview sources
#24242 opened Apr 24, 2026 by Yu-Zhewen Contributor Loading…
4
[Codegen][DMA] Fix XOR swizzle offset computation in gather-to-lds lowering
#24241 opened Apr 24, 2026 by Yu-Zhewen Contributor Loading…
[LLVMGPU] Fall back to scalar lowering for tiny attention shapes
#24239 opened Apr 24, 2026 by keshavvinayak01 Contributor Loading…
[VectorDistribute] Analysis to propagate promotion information
#24227 opened Apr 23, 2026 by sommerlukas Contributor Loading…
[IREEGPU] Introduce async_dma operation
#24226 opened Apr 23, 2026 by sommerlukas Contributor Loading…
3
[hal/local_task] Fix hang when command buffer ends with trailing barrier
#24225 opened Apr 23, 2026 by igornikolic-htec Loading…
1
[LinalgExt] Add OuterReduction tiling strategy for TopkV2Op
#24223 opened Apr 23, 2026 by bangtianliu Contributor • Draft
5
[Codegen] inner_tiled op: finish CPU support including scalable tiles.
#24218 opened Apr 22, 2026 by bjacob Collaborator Loading…
13
[DispatchCreation] Prevent fill->scatter cloning
#24214 opened Apr 22, 2026 by IanWood1 Member Loading…
1
8
[NFC] Outline the flattening logic in ContractToChainFMA
#24212 opened Apr 22, 2026 by amd-eochoalo Contributor • Draft
[NFC] Outline transpose part of ContractToChainFMA
#24211 opened Apr 22, 2026 by amd-eochoalo Contributor • Draft
[Draft][Codegen] Move DMA feasibility checks to ConfigUtils
#24208 opened Apr 22, 2026 by Yu-Zhewen Contributor • Draft
[DispatchCreation] Add gfx950-specific scale-only hoisting in HoistEncodingOps
#24204 opened Apr 22, 2026 by Muzammiluddin-Syed-ECE Contributor Loading…
[Codegen] Improve transfer_gather vectorization method.
#24201 opened Apr 21, 2026 by hanhanW Contributor Loading…
2
[Codegen] Enable software pipelining and XOR swizzling in DataTiledScaledMMAAttr path
#24199 opened Apr 21, 2026 by Muzammiluddin-Syed-ECE Contributor Loading…
[DT] Add no-hoisting flag with schedule-based tiling
#24198 opened Apr 21, 2026 by Muzammiluddin-Syed-ECE Contributor Loading…
4
[Codegen] Add unshuffled_operands attribute to DataTiledScaledMMAAttr
#24197 opened Apr 21, 2026 by Muzammiluddin-Syed-ECE Contributor Loading…
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.