-
I tried running an example similar to the checked in test [here](https://github.com/iree-org/iree/blob/main/tools/test/iree-run-module-multi.mlir) with the exception that I would like to run across GP…
-
This is an issue to track progress, feel free to close if there is a more descriptive issue of what needs to be done. CC: @jsetoain, @jamestcl-amd
Currently there is a 4x performance gap. See https…
-
command.log
```
PYTHONPATH=/home/chi/src/torch-mlir/build/tools/torch-mlir/python_packages/torch_mlir python runmodel.py --todtype default --mode onnx --outfileprefix opt-125M-awq 1> model-run.log …
-
### What happened?
While compiling int8 models, the generated IR gets converted to linalg and is canonicalized successfully. However, `iree-compile` crashes with the error
```
ElementsAttr does …
-
### Request description
When integrating only iree runtime in a project, IREE needs to be built with IREE_ERROR_ON_MISSING_SUBMODULES, otherwise it complains about not having submodules not require…
-
I'm seeing `iree-run-module` hang indefinitely with this call stack:
```
[Inline Frame] iree-run-module.exe!iree_futex_wait(void * expected_value, unsigned int) Line 148 (d:\dev\projects\iree\runtim…
-
Installed latest version of AMD drivers. Graphics card is: 7900 XTX
```
No vmfb found. Compiling and saving to D:\nodeai shark\euler_scale_model_input_1_512_512_rocm_fp16.vmfb
Configuring for dev…
-
I export clip torchIR by turbine, there is a line ir looks like:
"%2 = torch.vtensor.literal(dense_resource : tensor) : !torch.vtensor",
I use iree-opt's "torch-to-iree" pass to lower the torchIR to…
-
### What happened?
For Torch-mlir bump in IREE #18169
Compilation failure for onnx.Shape operator for CPU, GPU AMD (rocm + vulkan) and GPU Nvidia (cuda + vulkan)
CPU
Error Log:
```
_ IREE …
-
## Problem Description
The following IR
```mlir
module {
func.func @test(%arg0: tensor, %arg1: tensor) -> tensor {
%c0_i32 = arith.constant 0 : i32
%0 = tensor.empty() : tensor
%1 = lin…