-
Build StableHLO programs rather than XLA programs, ~~then we can provide support for anything that accepts StableHLO, including XLA and IREE~~ removing our dependency on XLA. This may require rewritng…
-
For attached IR, we are seeing assertion with give stack trace:
```
:0: error: invalid tensor dimension size
iree-compile: /proj/xhdhdstaff6/dhirajp/localBuild/iree/third_party/llvm-project/mlir/…
-
In IREE-Torch, there is one test that segfaults recently. The segfault is on memory access at address 0 before it falls off into ud2's in `printType`. Any ideas about build config/etc. that could expl…
-
👋 This dashboard summarizes my activity on the repository, including available improvement opportunities.
## Recommendations
_Last analysis: Jun 17 | Next scheduled analysis: Jun 24_
**NOTE**: I'v…
-
I'm trying to set up a CI flow that involves installing jax/jaxlib nightly and then also being able to checkout a corresponding commit in the source control system (i.e. to run more tests or build aga…
-
Please edit this comment to put in requests for terms to be explained in the MLIR glossary at https://mlir.llvm.org/getting_started/Glossary/
(source: : https://github.com/llvm/mlir-www/blob/main/w…
-
We are running into these issues when lowering torch.aten.view to linalg in these models (bart-large, mit-b0, t5-base, t5-large, ShuffleNet_v2_x2_0_vaiq_int8). Repro instructions can be found [here](h…
-
I tried using the hires fix, but it does not work. Here is the error that I get:
Traceback (most recent call last):
File "gradio\routes.py", line 488, in run_predict
File "gradio\blocks.py", …
-
First of all thank you very much for this repo.
I'm trying to build something like IREE's benchmark dashboard but I'm struggling with the demo.
I was able to spot some bugs after lots of debugging (…
-
Getting the following on my local branch off main from a187e05ae6ee535f6f69e4e50029de589148d254:
```
shark_tank local cache is located at C:\Users\skapusniak\.local/shark_tank/ . You may change th…