Skip to content

Pull requests: onnx/onnx-mlir

New pull request New
26 Open 2,352 Closed
26 Open 2,352 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

Fusion of Matmul add covering the stacked/unstacked/bcast1/bcast23 patterns
#3140 opened Apr 24, 2025 by AlexandreEichenberger Loading…
8
added support for Celu op
#3139 opened Apr 24, 2025 by logeshwaranmcw Loading…
6
Support --march=native
#3134 opened Apr 21, 2025 by chentong319 Loading…
Backward fold scale axis to Gemm layer in ONNX Dialect
#3131 opened Apr 18, 2025 by Arkar-Hema Loading…
5
Converting Split->conv->concat to Grouped conv
#3124 opened Apr 16, 2025 by kumarappan-cmyk Loading…
6
Combine parallel dense Optimization pass in ONNX Dialect
#3123 opened Apr 16, 2025 by Arkar-Hema Loading…
29
Combine Parallel Convolution optimization pass in ONNX Dialect
#3116 opened Apr 11, 2025 by Arkar-Hema Loading…
8
Set coordinate_transformation_mode=asymmetric when rewriting Upsample to Reshape to get same output.
#3096 opened Mar 17, 2025 by jorickert • Draft
LLVM update 43d71ba
#3086 opened Feb 21, 2025 by brnorris03 • Draft
15
Make verifyInputTensor true by default
#3079 opened Feb 17, 2025 by chentong319 • Draft
2
Reduce Runtime's dependence to LLVM (WIP)
#3071 opened Feb 9, 2025 by chentong319 • Draft
2
Update PyExecutionSessionBase.cpp to get right result
#3040 opened Jan 10, 2025 by fairytale0828 Loading…
3
Disabled building tests default (like LLVM), enabled for our CIs
#3021 opened Dec 2, 2024 by AlexandreEichenberger Loading…
11
Release MLIRContext and Module before executing opt command for memory reduction
#3000 opened Nov 5, 2024 by imaihal • Draft
3
Definition and shape inference for ONNXParallelOp and ONNXForkOp
#2810 opened May 1, 2024 by imaihal • Draft
8
[WIP] High-Level (Coase grain) parallelization with ONNXParallelOp and ONNXForkOp based on OpenMP
#2756 opened Mar 15, 2024 by imaihal • Draft
Loop collapsing with fusion
#2618 opened Nov 13, 2023 by chentong319 • Draft
patch for --EmitJNI on windows
#2582 opened Oct 25, 2023 by armgong Loading…
1
10
[Experiment] remove flag to disable hybrid pass
#2576 opened Oct 24, 2023 by sorenlassen • Draft
[NNPA] Check return values of zdnn calls. (follow-up of PR#2267)
#2338 opened Jun 27, 2023 by imaihal • Draft
12
use the same mmap for all tensors from the same external data file
#2331 opened Jun 21, 2023 by sorenlassen • Draft
add onnx op fields and remove OpBuildTable.inc
#2249 opened May 16, 2023 by sorenlassen • Draft
Fix JNI wrapper memory leak
#2178 opened Apr 19, 2023 by gongsu832 • Draft
14
[NNPA] AffineLoad and AffineStore from/to zTensor without zlow.stick and zlow.unstick
#1983 opened Jan 31, 2023 by tungld • Draft
4 of 5 tasks
Experimental: convert onnx to linalg
#1891 opened Dec 2, 2022 by chentong319 • Draft
7
ProTip! Add no:assignee to see everything that’s not assigned.