Skip to content

Pull requests: iree-org/iree

New pull request New
163 Open 15,659 Closed
163 Open 15,659 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

removes the check of large_model and opset_version
#20118 opened Feb 27, 2025 by amd-vivekag Loading…
1
Remove duplicated code for existing layout checks
#20117 opened Feb 27, 2025 by sgjzfzzf Loading…
[hip] Handle when devices cannot access peers, such as on Windows. hal/amdgpu Runtime AMDGPU HAL backend platform/windows 🚪 Windows-specific build, execution, benchmarking, and deployment
#20114 opened Feb 26, 2025 by ScottTodd Loading…
1
[Dispatch] Only bubble reshapes when possibly blocking fusion
#20108 opened Feb 26, 2025 by IanWood1 • Draft
13
Adding CloneToConsumersPass and ElideAsyncTransfersPass.
#20103 opened Feb 26, 2025 by benvanik • Draft
[Stream] Signal a failure if any recognized encoding cannot be resolved.
#20099 opened Feb 25, 2025 by hanhanW Loading…
3
[compiler] Fix reproducer generation/run
#20094 opened Feb 25, 2025 by devtbi • Draft
3
[runtime] Fix FromDLPackCapsule creating buffer with access ANY
#20092 opened Feb 25, 2025 by devtbi Loading…
6
Tune 4 more (to top 29) punet BS16 dispatches for MI325
#20089 opened Feb 24, 2025 by Max191 • Draft
1
Tentative E2E tests for gfx12, just copying gfx11 with relevant sed
#20084 opened Feb 24, 2025 by krzysz00 • Draft
[WIP] [stream] Add resource refcounting analysis pass
#20075 opened Feb 24, 2025 by drprajap • Draft
4
Stop forcing approximation of math.erf with --iree-codegen-gpu-native-math-precision
#20074 opened Feb 24, 2025 by bjacob Loading…
3
[DispatchCreation] Add pass to move non-fused encodings into dispatches.
#20071 opened Feb 23, 2025 by MaheshRavishankar Loading…
2
Create attention_and_matmul_spec_sdxl_fp8_mi325.mlir
#20069 opened Feb 23, 2025 by monorimet Loading…
1
[GPU] Update reshape propagation patterns to preserve fill and transpose
#20066 opened Feb 22, 2025 by nirvedhmeshram Loading…
5
Allow collapsing ops with index semantics
#20064 opened Feb 21, 2025 by IanWood1 • Draft
[DispatchCreation] Address missed horizontal fusion case with transposes
#20060 opened Feb 21, 2025 by MaheshRavishankar • Draft
[stream] Dedeplicate stream.yield values from stream.async.execute
#20056 opened Feb 21, 2025 by rsuderman Loading…
3
Changes to dispatch formation to allow for fusion with trunc in case of gemm + transpose gemm fusion
#20055 opened Feb 21, 2025 by MaheshRavishankar Loading…
11
[WIP] Add umbrella optimization flags
#20047 opened Feb 20, 2025 by IanWood1 Loading…
8
New flag: iree-codegen-math-transform-tweaks
#20042 opened Feb 20, 2025 by bjacob Loading…
7
Clarify error message for missing module dependencies. runtime/tools IREE's runtime tooling (iree-run-module, iree-benchmark-module, etc) runtime/vm IREE bytecode VM interpreter
#20036 opened Feb 19, 2025 by ScottTodd Loading…
1
Support cloning operand-less dispatches
#20025 opened Feb 18, 2025 by rsuderman Loading…
[DT] Add an option to not hoist infusible encoding ops out of dispatch.
#20017 opened Feb 18, 2025 by hanhanW Loading…
1
Allow expand shape propagation scross linalg ops with dynamic shapes.
#20014 opened Feb 18, 2025 by MaheshRavishankar • Draft
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.