-
the original code is as follow
```cpp
// Dispatch [5]: (V,M,K) x (V,N,K) => (V,M,N)
template
CUTE_HOST_DEVICE
void
gemm(MMA_Atom const& mma,
Tensor & D, // (V,M,N) Logical dat…
-
git version: c3d3cef8d5837
system: `Ubuntu 18.04.6 LTS`
reproduce with: `mlir-opt -one-shot-bufferize a.mlir`
a.mlir:
```
module {
func.func @test_reshape_3d_same_d2d_auto_empty(%arg0…
-
### Description
If you call `.item()` (or inadvertently call `.item()`) in torch, vmap will fail. This means supporting things like scalarloop are difficult when having anything vmap
```py
for …
-
### Context
OpenVINO component responsible for support of TensorFlow models is called as TensorFlow Frontend (TF FE). TF FE converts a model represented in [TensorFlow opset](https://www.tensorflow.o…
-
Doesnt appear to be any way to transfer a result tensor in to an existing cpu float array. Below requires new memory allocation.
var cpuResult = gpuResult.cpu();
float[] result = cpuR…
-
I am adding two new tensor methods related to NaN (is_nan and contains_nan). My unit tests are failing for burn-wgpu backend. See https://github.com/tracel-ai/burn/pull/2088 PR
**Describe the bug…
-
# Bug Report
### Is the issue related to model conversion?
No
### Describe the bug
My graph consists of a Concat node (with Axis=0) with two inputs with initializers. The first is initialized …
-
输入
c
name: c
tensor: float32[c_dynamic_axes_1,c_dynamic_axes_2,768]
f0
name: f0
tensor: float32[1,f0_dynamic_axes_1]
mel2ph
name: mel2ph
tensor: int64[1,mel2ph_dynamic_axes_1]
uv
name: uv…
-
https://github.com/iree-org/iree/commit/c80fa3bcabbaffab33281c997979ff84974cd843 adds the support for packing i1 back-to-back in storage behind an experimental flag. We've been struggling how to switc…
-
### 🐛 Describe the bug
Here, I came across this issue with MAISI network from MONAI.
To reproduce, you would need to pull branches from :
https://github.com/Project-MONAI/MONAI/pull/8153 and…