-
# Problem: We don't test onnx ops in our CI
- sometimes bad onnx lowering slip past code review
- SHARK-TestSuite catches some of them, but it's easy to improperly write test cases that don't actu…
-
### Describe the feature request
This request is very similar to the PR #15862 (integrate triton into ort). The only difference are the compilers and the details of metadata. They both use PTX/Cubi…
-
### What happened?
The compiler asserts on some models when trying to run TensorSliceOp::fold.
Error message:
```
ElementsAttr does not provide iteration facilities for type `mlir::Attribute`,…
-
Getting the following as of ad1a0f3 from the webui -- Adrenalin 23.9.3, RX 7900 XTX, SD 2.1 base, txt2img -- after clearing .vmfbs+shark_tank and doing `.\setup_venv.ps1 --force`
```
(shark.venv…
-
# Motivation
In turbine-models we have single export functions for different huggingface models -- each of these exports (and their respective CompiledModule instances) are parametrized by things l…
-
Whenever I try to compile the sdxl clip IR's linked in the playbook, iree-compile crashes on this line
```
%2 = torch.vtensor.literal(dense_resource : tensor) : !torch.vtensor
```
with a message t…
-
In a recent PR, the TopK e2e test fails in CI: https://github.com/iree-org/iree/actions/runs/11107992173/job/30867743807?pr=18634
The following test is what fails:
```
func.func @topk_2d_dim1_inv…
-
In [this ](https://gist.github.com/nirvedhmeshram/ce05292d502868404213abd88dc82531) working example we have
```
%6 = scf.forall (%arg0, %arg1) in (16, 80) shared_outs(%arg2 = %3) -> (tensor) {
%…
-
I'll beautify this once I get hold of Azure storage.
I have attached [gemma_7b.mlir](https://storage.googleapis.com/shark_tank/dan/Gemma/gemma_7b.mlir) along with [gemma weights](https://storage.go…
-
Request description
A compiler plugin currently lives here but needs setting a flag (IREE_COMPILER_PLUGIN_PATHS) at compiler time:
https://github.com/openxla/iree/tree/main/samples/compiler_plugins/…