-
开发机：ubuntu 20.04 mnn 3.0.0
模型 huggingface：Qwen2.5-0.5B-Instruct 和 Qwen2.5-0.5B-Instruct-GPTQ-Int8
## 导出 onnx 模型
$ python mnn/transformers/llm/export/llmexport.py --path pretrained_model/Qwen2.5…
-
The following:
```python
from numba import cuda
import numpy as np
@cuda.jit('void()')
def f():
x = cuda.shared.array(0, dtype=np.int32)
x.reshape(2, 2)
```
Gives:
```
Tra…
-
```fortran
program test_abs_2d_array
integer(8) :: x(2,2) = reshape([-1, 2, -3, 4], [2, 2])
print *, x
end program test_abs_2d_array
```
LFortran Error :
```
; ModuleID = 'LFortran'
s…
-
My DX12 game fails to run due to `E_INVALIDARG` being thrown by `CreateRootSignature()` when it's run via Reshape. Without Reshape, the function succeeds. `E_INVALIDARG` indicates that the blob that p…
-
### Checklist
- [ ] I have searched related issues but cannot get the expected help.
- [ ] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) b…
-
**Describe the bug**
Reshaping the tensor, which is currently in TILE_LAYOUT, is resulting in a low PCC value of -0.0015. We cannot switch the tensor to ROW_MAJOR_LAYOUT format because the subsequent …
-
Compare:
```
v = randn(728, 600)
w = randn(70, 728)
@time w * v # 0.017802 seconds (2 allocations: 328.172 KiB)
```
with:
```
v_ = reshape(reshape(v', 600, 728)', 728, 600)
w_ = resha…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf2.17.0
### Custom code
Yes
### OS platform and distribution
Ubuntu…
-
ttnn.reshape segfaults or gets stuck on some shapes after some time executing in a sweep
```
input_shape [38, 14] rehape_shape [19, 28] input_a_dtype DataType.BFLOAT8_B
Segmentation fault (core d…
-
The following test will fail with poor PCC:
```
def test_broken_reshape(device):
src_shape = (1, 56, 56, 64)
target_shape = (1, 1, 56*56, 64)
torch_input_tensor = torch.randn(src_shape, dt…