-
[Uplift PR ](https://github.com/tenstorrent/tt-xla/pull/63) failed due to
Investigating this locally I foun…
-
We could add badges for each test suite showing the number of tests, like those at https://github.com/onnx/onnx-mlir?tab=readme-ov-file#onnx-mlir
`FAILED: src/Accelerators/CMakeFiles/…
-
TBD
SpecializeGenericFunctionsPass fails on a UDF
SpecializeGenericFunctionsPass::specializeCallsInFunction(mlir::func::FuncOp)
```
#0 0x0000555558764980 in mlir::detail::walk(mlir::Operati…
-
It is possible to compile Sierra to MLIR https://github.com/lambdaclass/cairo_native to then execute it.
This kind of execution will be supported by Starknet.
Investigate the
- [ ] Performance cos…
-
With the latest torch (2.4) and iree-turbine, we are seeing this MLIR verification failure come up for a lot of our models during the export stage (aot.export).
Instructions to reproduce this error…
-
I have the following MLIR program:
test.mlir:
```
#map2 = affine_map (((d1 - (d1 + 2)) floordiv 8) mod 8)>
module {
func.func nested @func1() -> f32 {
%idx1 = arith.constant 1 : index
…
-
Sub-issue of https://github.com/tenstorrent/tt-mlir/issues/1033
-
When I train the model of dtype fp16 or mixed precision on V100 sxm2 16G, loss.backward() return error:
python: /project/lib/Analysis/Allocation.cpp:40: std::pair mlir::triton::getCvtOrder(mlir::A…
-
In `lib/Target/LLVM/NVVM/Target.cpp`, `NVPTXSerializer` compile `PTX` to binary with two different flows controlled by `MLIR_ENABLE_NVPTXCOMPILER`.
If building mlir with `-DMLIR_ENABLE_NVPTXCOMPILE…