-
### Compiler name
IREE
### Compiler version
latest
### Compiler language
C++, MLIR, LLVM
### Compiler homepage
https://openxla.github.io/iree/
### Motivation
The need for IREE is to have peop…
-
Full ONNX FE tracker is at: https://github.com/nod-ai/SHARK-Turbine/issues/564
## Running model
In alt_e2e test suite:
setenv CACHE_DIR "some Path where model will be downloaded"
If build…
-
# Error:
It seems to be expecting the kvcache page to be 4x smaller than it actually is:
```
INVALID_ARGUMENT; tensor shape dimension 1 mismatch; expected 1048576 but have 4194304; expected shape…
-
This issue is for the purpose of tracking all the ONNX Frontend Requirements.
### Instructions for finding the models/setup:
- [Linux server access](https://github.com/nod-ai/playbook/blob/main/HO…
-
VAE:
| Dispatch Type | Shape | Compilation Time [ms] | Execution Time [ms] |
| ------------- | ------------- | ------------- | ------------- |
| matmul | 256x65536x512 | 11968 | 1233 |
| matmul |…
-
Could start with what already exists, including the C++ binaries files and CMake build system:
* https://github.com/iree-org/iree/tree/main/tests/e2e/matmul
* https://github.com/iree-org/iree/tree…
-
For [this ](https://gist.github.com/nirvedhmeshram/344f11443b96fb9ff022fa283cc6cd8a) matmul like + elementwise IR, we go down the LLVMGPUSIMT pipeline, see dump [here](https://gist.github.com/nirvedhm…
-
### What happened?
for the given IR
```mlir
module {
func.func @torch_jit(%arg2: !torch.vtensor) -> !torch.vtensor attributes {torch.onnx_meta.ir_version = 7 : si64, torch.onnx_meta.opset_versi…
-
Below is the list of HF CNN fp32 model issues for [Full model list](https://gist.github.com/jinchen62/cdf54ef8ed725fcce9d6fa18ecbfa058). Tests are imported in https://github.com/nod-ai/SHARK-TestSuite…
-
### What happened?
I'm getting a register count overflow when trying to run llama3.1_405b_fp16 for 8 HIP devices targeting gfx942
```iree/runtime/src/iree/vm/bytecode/verifier.c:345: RESOURCE_EXHAUST…