-
Does oneflow support model offloading like pipe.to('cpu') while all the graphs are being loaded ?
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and f…
n1mda updated
2 weeks ago
-
### System Info
- `transformers` version: 4.41.2
- Platform: Linux-5.15.0-105-generic-x86_64-with-glibc2.29
- Python version: 3.8.10
- Huggingface_hub version: 0.23.4
- Safetensors version: 0.4.3…
-
`llm_inference` on local is throwing the below error for `gemma-2b-it-cpu-int8.bin` only `gpu` backend type is supported?
```
calculator_graph.cc:892] INVALID_ARGUMENT: CalculatorGraph::Run() fail…
-
Is there a way to support pipelines with CPU offloading enabled?
It seems currently unable to handle this condition
```python
import gc
import torch
from diffusers import StableDiffusion3Pipe…
-
When I run the sustechpoints annotation tool and use top to view, it mainly consumes CPU processes.
Is the operation of sustechpoints related to the CPU model?
My i5-13600k and i9-9900k runs smoothl…
-
When 8 processes are launched on a single server using torchrun, and each process executes from_pretrained() for a GPT-J 6B scale model, a CPU memory level OOM occurs.
-
Hi there.
Is there any way running eval_model.py with CPUs?
I am getting the error message:
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is Fa…
-
We recently discovered a performance issue with the apple m1 series in https://github.com/rust-lang/rust/issues/126937#issuecomment-2226834122. I believe this is due to EarlyIfConversion using an outd…