-
I'm not sure if the 200/500 comes from the extensive request LLM? if so, can I reduce the request num or wait longer time or modify ollama server model cfg? and how. Thanks
**python builder/index…
-
### 🚀 The feature, motivation and pitch
PyTorch does not seem to provide wrappers to mixed precision algorithms in e.g MAGMA (dshpov, shportf) and cuSolver (https://docs.nvidia.com/cuda/cusolver/inde…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What would your feature do ?
can use a Dual GPU setup.
### Proposed wor…
-
遇到的问题：
如题，我尝试在一台旧电脑中实装该项目的时候，会一直报错
“RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
There are stats for the Raspberry Pi GPU in `/sys/kernel/debug/dri//gpu_usage`, and per-process stats in `/sys/ke…
-
In my case, I have multiple SegmentAnythingUltraV2 nodes, processing different images, and I wanted to use cache_model to improve speed, but found that the final GPU usage was N* cache_model .
Can …
-
Hello author, do you encounter situations where GPU utilization is very low during training?
-
The VM GPU device is not always needed and having it enabled comes with additional memory overhead and bigger attack surface. Being able to easily disable it would make it simple to pack more VMs on a…
-
Hi, thanks for the app. It is awesome.
I have a new freeze behavior (used to work without freeze) : the graphic card no longer render screen and show a green or black color screen, and stay stuck l…
-
Even though I'm using a gpu build, inference is running on cpu/ram. I tried to tinker with parameters, but with no luck.
Log:
```
Godot Engine v4.3.stable.mono.official.77dcf97d8 - https://go…