-
https://github.com/nod-ai/SHARK-TestSuite/issues/182
After Integrate torch-mlir@ec6d7aa onnx.resize op https://github.com/iree-org/iree/pull/17358:
@zjgarvey looks like quantize related error, it…
-
We need a CI that runs all tests + presubmit checks, etc... all the goodies we have in IREE core.
-
Failer op in [Inception_v4_vaiq_int8.default.onnx.torch.elide.mlir](https://gist.github.com/AmosLewis/c9b0933d0d1d69176d89298e7b1ff8b5#file-inception_v4_vaiq_int8-default-onnx-torch-elide-mlir)
- ht…
-
### What happened?
I'm trying to compile [`singlepose-lightning-tflite-int8` tensorflow lite file](https://www.kaggle.com/models/google/movenet/tfLite/singlepose-lightning-tflite-int80). These are …
-
**System information**.
TensorFlow version (you are using): N/A
Are you willing to contribute it (Yes/No): Not immediately.
**Describe the feature and the current behavior/state**.
In some o…
-
Hi,
I'm trying to run the torch imported fp16 stable diffusion model and it seems to crash in the importing stage. Here's the commandline I used:
```
python main.py --precision="fp16" --prompt=…
-
Other MLIR repositories such as mlir-hlo support using the LLVM_EXTERNAL_PROJECTS (https://github.com/tensorflow/mlir-hlo/blob/master/CMakeLists.txt#L93) as a build mechanism for plugging in the provi…
-
We should have a hostcall interface, as it'll enable many future developments (I/O, GC, etc). Probably needs both a blocking and non-blocking version, and maybe the ability to queue up multiple calls …
-
The following error occurs running the pytorch-sourced efficientnet-b0 model on CUDA backend
```
E RuntimeError: Error registering modules: c/runtime/src/iree/hal/drivers/cuda/native_executable…
-
Currently the iree_linalg_ext.pack operations which map well to the aie dma operations are decomposed to air.dma_memcpy_nd which doesnt seem to model it as well since it doesnt have a concept of wrap …