-
For the given IR
```mlir
module {
func.func @torch_jit(%arg0: !torch.vtensor, %arg1: !torch.vtensor, %arg2: !torch.vtensor) -> !torch.vtensor attributes {torch.onnx_meta.ir_version = 7 : si6…
-
For example with the ClangIR of the day https://github.com/llvm/clangir/commit/bae7bd9e68764afb586040f6d63b3759e0b6d856 on https://github.com/llvm/clangir/blob/main/clang/test/CIR/Lowering/ThroughMLIR…
-
Step1: Change this [line](https://github.com/nod-ai/iree-amd-aie/blob/c15a45a016a504f032b0f5c02d64c9916da91521/build_tools/build_test_cpp.ps1#L61) from
"-DCMAKE_BUILD_TYPE=Release"
to
"-DCMAKE_BUIL…
-
I build tt-mlir with
`cmake -G Ninja -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER=clang-17 -DCMAKE_CXX_COMPILER=clang++-17 -DTTMLIR_ENABLE_RUNTIME=ON`
`cmake --build build`
![Image](https:…
-
With the latest LLVM integration from https://github.com/openxla/stablehlo/pull/2635, building llvm-project for stablehlo leads to the following compilation error:
```
$ MLIR_ENABLE_BINDINGS_PYTHON=…
pearu updated
2 hours ago
-
https://github.com/llvm/llvm-project/blob/e52238b59f250aef5dc0925866d0308305a19dbf/mlir/lib/Dialect/Mesh/Transforms/Spmdization.cpp#L98
It should probably be "remainingPartialAxes" instead of "allRed…
-
准备好环境后sophon-demo/sample/StableDiffusionXL/scripts，执行./get_unet_bmodel.sh里的get_unet_bmodel.sh时，生成mlir成功了，但mlir到bmodel时出错了，具体报错信息如下：
[Running]: tpuc-opt unet_base_bm1684x_bf16_final.mlir --codegen="mo…
-
**Describe the bug**
I am trying to include the `pybind11` vcpkg port in a CMake project that also depends on MLIR (which I don't include via vcpkg). Both work independently, but when used together, …
-
No broadcast op is getting called, and it's expecting from device to perform the broadcast `%2 = "ttnn.from_device"(%1) : (tensor) -> tensor`
```
#device = #tt.device, l1Map = (d0, d1)[s0, s1] -> (0,…
-
### What happened?
This issue seen while debugging some other failures in ONNX model. For the give IR
```mlir
module {
func.func @torch_jit(%arg2: !torch.vtensor) -> !torch.vtensor attributes {tor…