-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar feature requests.
### Description
Non-specialized …
-
/kind feature
**Describe the solution you'd like**
To autoscale LLM inference services Knative's request level metrics may not be the best scaling metrics as LLM inference is performed at the toke…
-
I appreciate your wonderful work!
I have a question related to memory bank. In SAM2 paper, a memory bank includes two kinds of FIFO queue (recent frames, prompted frames), and corresponding object …
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
### Describe the issue
I quantized a simple CNN model in Pytorch and converted it to onnx. When I tested the runtime of int8 model and fp32 model on CPU, the int8 model was slower. Here my code:
[Go…
-
Hello, I saw the previous comment about the recommended Yolov8 models. You did mention about the image size 320. When it comes to image size 320, how many epochs and batch size do you recommended? Or …
-
Consider the following MWEs:
```modelica
model WrongClocked1
Real x1;
Real x2;
equation
x1 = sin(time);
when Clock(0.1) then
x2 = x1;
end when;
end WrongClocked1;
```
This mo…
-
Windows 11 64bit, WSL Ubuntu, RTX 3080 10gb vram
Hey, not sure anyone still checks this but I've cobbled the environment together after a lot of trial and error and have it working on gradio. The o…
-
### 🐛 Describe the bug
Following the [tutorial](https://pytorch.org/tutorials/intermediate/realtime_rpi.html) the program stops with
`[1] 182488 illegal hardware instruction (core dumped)`
…