Skip to content

Pull requests: iree-org/iree

New pull request New
72 Open 16,846 Closed
72 Open 16,846 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

Test int-range analysis poison support
#21642 opened Aug 10, 2025 by Hardcode84 • Draft
[docs] Add documentation for updating golden outputs
#21641 opened Aug 9, 2025 by efric Loading…
7
[WIP][Codegen] Lower preference for warp reduction pipeline
#21640 opened Aug 8, 2025 by newling • Draft
[GlobalOpt] Sink transposes with multiple uses
#21639 opened Aug 8, 2025 by IanWood1 • Draft
[Codegen][GPU] Use arithmetic intensity to guide gemm size categorization
#21638 opened Aug 8, 2025 by jerryyin Loading…
[ROCM] Add ukernel descriptor lowering to pipeline
#21634 opened Aug 8, 2025 by jtuyls Loading…
2
Adding iree_hal_device_queue_dispatch. hal/api IREE's public C hardware abstraction layer API
#21630 opened Aug 8, 2025 by benvanik Loading…
1
Unifying dispatch/dispatch_indirect and adding extended configuration. hal/api IREE's public C hardware abstraction layer API
#21627 opened Aug 8, 2025 by benvanik Loading…
2
[GPU][DT] dce unused tensor.dim ops in SpecializeExports
#21624 opened Aug 7, 2025 by jtuyls Loading…
1
8
Adding semaphore creation and wait flags for controlling behavior. hal/api IREE's public C hardware abstraction layer API
#21619 opened Aug 7, 2025 by benvanik Loading…
1
Integrate llvnm-project@ff616a19
#21614 opened Aug 7, 2025 by krzysz00 Loading…
6
[codegen][gpu] Guard vector.trasfer_write with conditional in vector distribute if not distributed
#21603 opened Aug 6, 2025 by fabianmcg Loading…
1
[LLVMGPU] Move LLVMGPUVectorLowering after OptimizeIntArithmetic
#21597 opened Aug 5, 2025 by Max191 • Draft
Numerical tests: softmax with dynamic reduction size
#21594 opened Aug 5, 2025 by newling Loading…
[Stream] Special handling in partitioning for transfer with pinned affinity
#21589 opened Aug 5, 2025 by ziereis • Draft
[Codegen] Select for pad value just before yielding
#21581 opened Aug 4, 2025 by newling Loading…
16
Toggle the default option to false for pre-padding convolution flag
#21579 opened Aug 4, 2025 by yzhang93 Loading…
[Codegen] Add XOR-based Swizzle Attribute
#21562 opened Aug 1, 2025 by sebvince • Draft
3
Pad with correct value
#21557 opened Aug 1, 2025 by newling • Draft
Add support for ml_dtypes to python runtime bindings
#21549 opened Jul 31, 2025 by rsuderman Loading…
1
[Dispatch] Don't clone scatter's indices
#21534 opened Jul 30, 2025 by IanWood1 Loading…
[WIP] Add IGEMM configuration to SPIRV
#21531 opened Jul 30, 2025 by giacs-epic • Draft
[codegen] more consumer fusion
#21521 opened Jul 29, 2025 by ftynse Loading…
3
[CODEGEN] Adding pipeline path to take Direct Convolution
#21519 opened Jul 29, 2025 by YashDeshpande25 • Draft
1
[Codegen][LLVMGPU] Add a DropVectorUnitDims call
#21511 opened Jul 28, 2025 by krzysz00 Loading…
5
ProTip! What’s not been updated in a month: updated:<2025-07-10.