-
Currently we pin torch to 2.2.0 to resolve issues with `dgl`, which is required by `matgl` (M3GNet), but increasingly becoming a problem.
If we only update torch to 2.4.0, poetry installs everythin…
-
Hello, I'm trying to reload a model after quantizing it and saving it to a checkpoint file + the quantization map:
```
import json
import torch
import diffusers
import optimum.quanto
from op…
-
/content/ComfyUI/models/text_encoders/t5xxl_fp16.safetensors
/content/ComfyUI/models/unet/flux1-dev-bnb-nf4-v2-unet.safetensors
/content/ComfyUI/models/unet/flux1-schnell-bnb-nf4-unet.safetensor…
-
https://github.com/layer6ai-labs/dgm-eval/blob/master/dgm_eval/metrics/fd.py
structure
```python
import torch
from torchmetrics import Metric
class MyAccuracy(Metric):
def __init__(s…
-
This model was working till 1114 and started failing from 1115, seems like torch-mlir bump has caused this issue
```mlir
module {
func.func @main_graph(%arg0: !torch.vtensor ) -> !torch.vtens…
-
I'm attempting to run inference on a GPU using the layout predictor.
I have made the following changes to the code.
```
class LayoutPredictor:
# ... (previous code) ...
def __init__(sel…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
Trai…
-
Currently, neither vanilla torch nor array-api-compat torch seem to accept the `copy` keyword. (Or the `device` keyword, of course, but that is probably harder to deal with.)
```python3
import num…
-
Is it possible to export models with complex weights? If so, how would I do that? For example,
```python
class cLinear(nn.Module):
def __init__(self, in_features, out_features, bias=True):
…
-
When starting python app.py I get this error:
NameError: name 'is_torch_npu_available' is not defined. Did you mean: 'is_torch_xla_available'?