iree
iree copied to clipboard
iree-org
A retargetable MLIR-based machine learning compiler and runtime toolkit.
### What happened? For Torch-mlir bump in IREE #18169 Runtime failure - input OUT_OF_RANGE for test_maxpool_2d_uint8 on GPU NVidia Vulkan Passes in GPU Nvidia Cuda, CPU, GPU AMD (rocm +...
### What happened? For Torch-mlir bump in IREE #18169 Runtime failure - zeros output for test_shape_clip_start on CPU, GPU AMD vulkan, GPU Nvidia (cuda+vulkan) ``` _ IREE compile and run:...
### 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:...
### What happened? I converted an ONNX model resnet50-v1-12-int8.onnx to mlir using import_onnx tool that completed successfully. `python -m torch_mlir.tools.import_onnx resnet50-v1-12-int8.onnx -o restnet50-v1-12.int8.onnx.mlir` However when converting the torch-onnx to torch...
### What happened? Hello! I have been trying to `iree-compile` a converted onnx model, but I hit this error: ``` error: failed to legalize operation 'torch.operator' that was explicitly marked...
This switches the pass generation definition to tablegen. The cleanup includes switching passes to follow the `create*Pass` naming convention and introduces anonymous namespaces. Some passes are still defined in `Passes.h`...
The revision sets up a path to generate GPU layouts on CPU backends. The revision uses `--iree-gpu-test-target` flag to control the target GPU. Note: both `--iree-codegen-cpu-experimental-emulate-gpu-data-tiling` and `--iree-gpu-test-target` flags are...
### Request description E2E tests suite for the Attention that has reference implementation in it. ### What component(s) does this issue relate to? Compiler ### Additional context I raised a...
We are not generating documentation for passes. Only for dialect ops, attributes, etc. This is meant to serve as a pattern example that can be used for other dialects' passes.
