-
check file
[ar_MobileNetV2_int8_c_demo_v0.zip](https://github.com/BR-SW/iree_samples/files/14717962/ar_MobileNetV2_int8_c_demo_v0.zip)
```
> tree
.
|-- main
|-- main.c
|-- main.c.extern.h
…
-
I've progressed through building IREE and running tests on Android, but I've encountered an issue where only Vulkan-related test codes are consistently failing. I've checked the Vulkan information on …
-
### What happened?
This looks like a case of unregistered dialect.
Context :-
In the combined llama IR it fails in compilation stage (for CPU backend) with the following command where I'm using…
-
### What happened?
iree/tests/e2e/regression/check_regression_llvm-cpu_lowering_config.mlir test hangs forever in RISC-V 64bit Linux QEMU emulation
### Steps to reproduce your issue
1. Cherry-pick …
-
Many issues hit when loading a lot of parameters:
```
iree-run-module --parameters=model=ggml-model-f32.gguf --module=global_Llama_2_7b_chat_hf.vmfb --function=run_initialize --input=1x5xi64=1,44…
-
### What happened?
I exported a model from JAX to MLIR using shape polymorphism in the batch index, but ran into the following issue when I tried to compile on a Windows machine:
```
PS C:\Users\be…
-
### What happened?
If the pass `iree-util-hoist-into-globals` is run more than once, it produces hoisted globals without a value. When `consteval` is then run, it produces the error `internal error…
-
### What happened?
For [Vae model](https://storage.googleapis.com/shark_tank/SDXL/mlir/vae_1_77_1024_1024_fp32_stable-diffusion-xl-base-1.mlir) I get the following runtime error :-
```
INTERNAL; CU…
-
It looks like Gemma can only run on Pixel 8 if we use the non-DT path for now. Using DT or DT+UK leads to a SIGABRT signal which is probably due to running OOM. This is the info I can see in the tombs…
-
Recently I'm trying to run the model compiled by onnx-mlir on GPU.
Here is my idea about the compilation flow:
affine/scf/std Dialect -> gpu Dialect ->NVVM IR -> LLVM IR -> ptx assemble.
I have no …