Skip to content

Pull requests: iree-org/iree

New pull request New
204 Open 18,700 Closed
204 Open 18,700 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

[LinalgExt] Fix attention NaN for fully-masked rows
#24178 opened Apr 21, 2026 by keshavvinayak01 Contributor • Draft
1
@keshavvinayak01
1
[TMTensor] Lower TMTensor::AttentionOp directly to OnlineAttentionOp
#24177 opened Apr 21, 2026 by keshavvinayak01 Contributor • Draft
Split ContractToChainFMA
#24174 opened Apr 20, 2026 by amd-eochoalo Contributor • Draft
1
[DispatchCreation] Allow fusion of multi-result producers
#24169 opened Apr 20, 2026 by keshavvinayak01 Contributor Loading…
1
Build without benchmark
#24167 opened Apr 20, 2026 by AaronStGeorge Contributor • Draft
[DispatchCreation] Fuse a scalar reduction with parallel consumer when they share an input.
#24166 opened Apr 20, 2026 by Abhishek-Varma Contributor Loading…
1
3
amdgpu: barrier command-buffer packets after inline waits
#24163 opened Apr 19, 2026 by stellaraccident Collaborator • Draft
[Codegen] Add transfer_{gather/scatter} unrolling and lowering to CPU backend
#24155 opened Apr 17, 2026 by NoumanAmir657 Contributor Loading…
7
[Tokenizer] Fix infinite loop when encountering a special token in partial segment mode
#24150 opened Apr 17, 2026 by Finistere Loading…
[CI] Cache bazel builds
#24145 opened Apr 16, 2026 by amd-eochoalo Contributor Loading…
5
[Codegen] Refactor MMA attr filtering and root op selection into util function
#24144 opened Apr 16, 2026 by RattataKing Contributor • Draft
[LinalgExt][DMA] Support padded im2col async-copy with zero pad_value
#24142 opened Apr 16, 2026 by lialan Contributor • Draft
[Codegen][GPU] Fix f32 attention compilation failure when head_dim=128
#24138 opened Apr 16, 2026 by keshavvinayak01 Contributor Loading…
1
5
[Codegen] Move scatter DPS fill into workgroup forall
#24136 opened Apr 16, 2026 by ziliangzl Contributor Loading…
9
[draft] [do not review] unrolling transfer_read transfer_write
#24134 opened Apr 15, 2026 by amd-eochoalo Contributor • Draft
Some fixes to work around a bug in cmake, and isa naming
#24131 opened Apr 15, 2026 by AWoloszyn Contributor Loading…
2
[LinalgExt] Add TilingInterface support for TopkV2Op
#24129 opened Apr 15, 2026 by bangtianliu Contributor Loading…
8
[Codegen][LinalgExt] Port attention rewrites to OnlineAttentionOp
#24123 opened Apr 15, 2026 by keshavvinayak01 Contributor • Draft
compiler/plugins/input/TOSA: fix: TOSA arith lowering must handle apply scale introduced by linalg lowering
#24121 opened Apr 15, 2026 by Manewing Contributor Loading…
2
[Codegen] Enable DMA by default for F16/BF16 Gemm on gfx950
#24117 opened Apr 14, 2026 by Yu-Zhewen Contributor Loading…
13
[Codegen][GPU] Remove the single-iteration workaround and distribute pad-fused copies
#24116 opened Apr 14, 2026 by jerryyin Member • Draft
2
[runtime/python] Remove forced HOST_VISIBLE from AllocateBufferCopy
#24106 opened Apr 14, 2026 by jtuyls Contributor Loading…
1
1
[GPU][Codegen] Choose VDMFMA intrinsics for 16bit input skinny gemms
#24103 opened Apr 14, 2026 by efric Member • Draft
4
[Codegen] Add VectorDistribute constraint generation scaffolding for matmul and conv
#24093 opened Apr 13, 2026 by RattataKing Contributor Loading…
27
[Codegen][Heuristics] Update seeds to be closer to triton base case (preshuffling prs 3/3)
#24089 opened Apr 13, 2026 by Muzammiluddin-Syed-ECE Contributor • Draft
ProTip! Exclude everything labeled bug with -label:bug.