-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
Hi,
When using the precompiled binary and Weights for Phi-2, the error is following.Could you share how to use it ?
Precompiled Bina…
-
### Version of Awkward Array
main
### Description and code to reproduce
This is *not* a priority right now, as we long-term have plans to work on the build backend, but this issue should serv…
-
## 🐛 Bug
iOS MLC Chat app crashes when trying to use downloaded custom Llama2 model.
## To Reproduce
Steps to reproduce the behavior:
1. Compling the model with TVM Unity and recommended …
-
The [C API doc](https://dmlc.github.io/dlpack/latest/c_api.html#_CPPv4N15DLManagedTensor7deleterE) doesn't state whether the `deleter` callback can expect the GIL to be already acquired, or should do …
-
Not really an issue but, I'm trying to populate a struct in constant memory containing (device) pointers in order to run my kernel through kernel tuner. In C the struct looks something like:
```c++
…
-
**Describe the bug**
When the model starts to analyze any given sentence, run stops with the following error code:
```
Traceback (most recent call last):
File "/home/istvanu/PycharmProjects/A…
-
### Describe the issue:
Numpy only consumes arrays with dlpack and dlpack_device dunders (torch and jax arrays). It can't consumes PyCapsule which makes it not compatible with frameworks which only…
-
After I compile a torch model using hidet and use the CPU() function on the output tensor. It is slow compared to CPU() function used on original torch model output tensor. This negates the speed up a…
-
## 🐛 Bug
`torch.utils.dlpack.to_dlpack` no longer works for Boolean Tensor.
## To Reproduce
```python
torch.utils.dlpack.to_dlpack(torch.BoolTensor([False, True])) # Bool type is not suppo…
-
Hello rapids_singlecell team,
I am encountering an issue while running analysis using rapids_singlecell on a system equipped with two A100 80G GPUs. Despite having ample GPU memory available (not e…