-
So, on the down-low, I've been building a native Python->IREE compiler frontend. And since I got the lowerings minimally working today (it doesn't do much, since most interesting things require runtim…
-
This issue is in preparation to kick off QA to complete by 11/15/2024. The three workflows that need to be documented are the following (assumes user has already done basic installation which has alre…
-
-
So, we have implemented a workaround for handling a particular case of dynamic dimension support for broadcast op : [workaround patch](https://gist.github.com/vivekkhandelwal1/f5cba043bf3bf08967a5fd2…
-
Much love to all the new work on img to img and automating the base model identity working on rdna2 and 3... but 593 broke my merged models I work with. I see it now will delete the existing and recom…
-
```
E iree.compiler.tools.binaries.CompilerToolError: Error invoking IREE compiler tool iree-compile
E Diagnostics:
E /data/anush/actions-runner/_work/SHARK/SHARK/shark.venv…
-
I have successfully executed the shark project using the llama large language model, and it works well. The model was sourced from shark_tank in MLIR format. I would like to run another large language…
-
_(filing this to track ideas and see if there is community interest)_
## Background
IREE is designed to take the "ML" out of "ML deployment" and just turn "running an ML model" into "running som…
-
IREE currently lacks support for fusing `LinalgExt` operations with either other `LinalgExt` operations or standard `Linalg` operations..The current fusion implementation relies on indexing maps to de…
-
The pack-peel pipeline, matmul (m=n=1024, k=512) followed by addition of a bias (1-d vector with 1024 values) results in the final allocations (I've renamed the SSA values for clarity).
```
%bi…