Skip to content

Pull requests: iree-org/iree

New pull request New
149 Open 15,452 Closed
149 Open 15,452 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

[LLVMGPU] Correct the workgroup level tile sizes for WarpReduction
#19819 opened Jan 26, 2025 by pashu123 Loading…
8
Adding stream.tensor.dispatch op. compiler/dialects Relating to the IREE compiler dialects (flow, hal, vm)
#19817 opened Jan 25, 2025 by benvanik Loading…
1
Disable Attention V operand transposition.
#19810 opened Jan 24, 2025 by MaheshRavishankar Loading…
[LLVMGPU] Enable Matvec through vector distribute pipeline
#19807 opened Jan 24, 2025 by pashu123 • Draft
DNS - Turn on SpecializeEncoding pass by default.
#19805 opened Jan 24, 2025 by hanhanW • Draft
[Codegen][GPU] Infer workgroup size multiples from producers and consumers
#19804 opened Jan 24, 2025 by Max191 Loading…
3
Add support for executable duplication in encoding specialization pass.
#19803 opened Jan 24, 2025 by hanhanW Loading…
8
bump tracy to wolfpld/tracy@5479a42
#19801 opened Jan 24, 2025 by dezhiAmd Loading…
8
[Codegen][Tuner] populate the tuning spec for MI308X
#19800 opened Jan 24, 2025 by bangtianliu Loading…
Add pattern to convert generic conv ops to IGEMM
#19798 opened Jan 23, 2025 by nirvedhmeshram • Draft
3
[runtime][python] Allow benchmark to accept file path, not just a VmModule
#19793 opened Jan 23, 2025 by sogartar Loading…
Switch to upstream StablehloToLinalg code. cleanup 🧹 integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#19792 opened Jan 23, 2025 by ScottTodd Loading…
11
[AMDGPU] Use shared memory in multi_mma ukernel
#19786 opened Jan 23, 2025 by bjacob • Draft
11
[GPU] Force distribution along workgroups for scatter
#19784 opened Jan 23, 2025 by qedawkins Loading…
Move ASM to the end of languages list in CMakeLists.txt
#19781 opened Jan 23, 2025 by javidcf Loading…
[Dispatch] Enable fusing producers with scatter
#19775 opened Jan 22, 2025 by IanWood1 Loading…
1
[VectorExt] make fold unit dims work with dynamic shape
#19771 opened Jan 22, 2025 by manupak Loading…
3
[Codegen] Swap to IREE's extract_strided_subview patterns
#19757 opened Jan 21, 2025 by krzysz00 Loading…
6
Remove barriers post execution scheduling
#19742 opened Jan 20, 2025 by rsuderman Loading…
1
Update regression mi300 test to use Conductor
#19738 opened Jan 19, 2025 by yamiyysu Loading…
5
[linalgExt::Attention] Move scale out of AttentionOp
#19737 opened Jan 19, 2025 by ita9naiwa Loading…
1
[Stream] Add layouts to encodings for all stream tensor AffinityOp.
#19726 opened Jan 17, 2025 by hanhanW Loading…
6
Revert "[hip] Try again to fix the semaphore busy loop."
#19722 opened Jan 16, 2025 by AWoloszyn • Draft
[GlobalOptimization] Do not hoist fill-like operations
#19719 opened Jan 16, 2025 by Groverkss • Draft
[DispatchCreation] Bubble expand_shape for multi use producers
#19718 opened Jan 16, 2025 by Groverkss Loading…
5
ProTip! Adding no:label will show everything without a label.