-
Notifications
You must be signed in to change notification settings - Fork 637
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Assertion `input.size() == permutation.size() && "expected input rank to equal permutation rank"' failed #17734
Comments
The sharktank llama model (nod-ai/shark-ai#22) is failing with this same error. Stack with more context:
|
Possible culprit: llvm/llvm-project#93529 |
Confirmed - my issue does not occur with that PR reverted. Going to dig a bit deeper then comment there. |
It is not enabled until the upstream commit: llvm/llvm-project@a945f55 The upstream commit triggers a bug in IREE, so the revision disables the propagation. See #17734 for more details. --------- Signed-off-by: hanhanW <[email protected]>
Putting a note here: llvm/llvm-project#96697 exposes the control of (producer, consumer) pair to controlFn API. #17740 contains the IREE fix for the upstream change. I have a local patch which re-enables the pack->expand_shape propagation in IREE. |
mit-b0 issue goes away as well with revert this llvm/llvm-project#93529
|
Fixed by llvm/llvm-project#96732 need bump |
It was disabled because of an upstream bug. After adding more control on the control function, we no longer need the workaround. The revision flips the behavior to what it was. Issue: iree-org#17734 Signed-off-by: hanhanW <[email protected]>
It was disabled because of an upstream bug. After adding more control on the control function, we no longer need the workaround. The revision flips the behavior to what it was. Issue: #17734 Signed-off-by: hanhanW <[email protected]>
It is not enabled until the upstream commit: llvm/llvm-project@a945f55 The upstream commit triggers a bug in IREE, so the revision disables the propagation. See iree-org#17734 for more details. --------- Signed-off-by: hanhanW <[email protected]> Signed-off-by: Lubo Litchev <[email protected]>
What happened?
mit-b0 pytorch model to onnx failed
nod-ai/SHARK-TestSuite#270
pytorch/models/mobilebert-uncased
pytorch/models/t5-base
pytorch/models/t5-large
has the same issue
gdb backtrakce output:
Steps to reproduce your issue
input ir: mit-b0.default.pytorch.linalg.elide.mlir
/home/chi/src/iree-build/tools/iree-compile --iree-input-demote-i64-to-i32 --iree-hal-target-backends=llvm-cpu mit-b0.default.pytorch.linalg.elide.mlir > mit-b0.default.vmfb 2>iree-compile.log
What component(s) does this issue relate to?
Compiler
Version information
iree candidate-20240624.934
Additional context
No response
The text was updated successfully, but these errors were encountered: