-
### Describe the issue
Hello,
see [also this discussion](https://github.com/microsoft/onnxruntime/discussions/22427). I'm opening this one as I think it's an issue as sifting through previous issues…
-
Currently, 7b and 14b models take 10s and 15s respectively to load. Pretty much the same as a vanilla rwkv does.
It would a great thing to make those models to load as fast as possible which could le…
-
We (some folks from the functorch team, @samdow @Chillee) met with some of the PyTorch GitHub first and dev infra teams (@malfet, @osalpekar, @seemethere) to discuss pytorch/pytorch and functorch co-…
-
### 🐛 Describe the bug
There's an overload `func: to.dtype_layout(Tensor(a) self, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, bool non_blocking=False, …
-
It will likely require converting them to HF format/Pytorch, similar to how it's done for the OPUS-MT and HPLT models:
https://huggingface.co/Helsinki-NLP/opus-mt-zh-en
https://huggingface.co/HPLT…
-
### Context
Currently, we receive segfault during creation of string type constant:
```
import openvino.runtime.opset14 as ov
import numpy as np
str_const = ov.constant(np.array(['openvino'], d…
-
Hey, this is not so much an issue as a place to solicit public feedback.
I think we should implement type conversion from the amrex FArrayBox (or more precisely the Array4) data type to numpy.ndarray…
-
how to use the bilateral_slice.cu.cc
-
I am trying to model a protein homodimer complexed with dsDNA. I have entered in the two identical protein monomer chains as separate files and DNA strands as two separate files. In a command similar …
-
**Summary.** The functions in `torch.cuda.nvtx` can currently be associated with ASCII text only. However, the NVIDIA APIs permit more options, including custom colors. http://docs.nvidia.com/cuda/pro…