-
Notifications
You must be signed in to change notification settings - Fork 514
Pull requests: llvm/torch-mlir
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[ONNX] Add per channel quantization support for Onnx.QLinearConv op
#3917
opened Dec 13, 2024 by
vivekkhandelwal1
Loading…
Wrap indices to be within max range for as_strided + index_select
#3902
opened Dec 3, 2024 by
sahas3
Loading…
CMakeLists.txt: Fix bad include paths in torch_mlir_target_includes
#3897
opened Dec 2, 2024 by
mgehre-amd
Loading…
Fix output size computation for MaxPool2D for ceil_model = true.
#3890
opened Nov 22, 2024 by
sahas3
Loading…
[ONNX] reduce min opset versions for Greater and Gather
#3877
opened Nov 15, 2024 by
zjgarvey
Loading…
Augmented calls to yaml.load to use the safe loader.
#3825
opened Oct 29, 2024 by
TimAtGoogle
Loading…
Augmented calls to yaml.load to use the safe loader.
#3817
opened Oct 24, 2024 by
TimAtGoogle
Loading…
[Torch] Decompose torch.take op into AtenFlattenUsingInts and AtenSel…
#3761
opened Oct 4, 2024 by
bratislavSyrmia
Loading…
[TorchToLinalg] Fix AtenReflectionPad2dOp lowering to not assert when dimensions unknown
#3758
opened Oct 3, 2024 by
giacs-epic
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.