-
### Motivation.
At a high level, we at Neural Magic are writing a custom compiler for Torch Dynamo to define a system within vLLM where we can write graph transformations. The main goal is a separa…
-
**Is your feature request related to a problem? Please describe.**
My understanding of the documentation and the code is that `llm-guard` will lazy-load the models required by the chosen scanners fro…
-
Hello, I'm trying to train YOLOv8-large in int4 format. I took the training recipe available at [sparsezoo](https://sparsezoo.neuralmagic.com/models/yolov8-l-coco-pruned85_quantized?hardware=deepspars…
-
Hello, first of all thanks a lot for this repo, I have one question:
I am doing my own object detection using your google colab, I load my dataset and train it using your script. But when I run the a…
-
Orders of magnitude performance increases have been observed: https://github.com/mlcommons/inference_results_v3.0/tree/main/open/NeuralMagic
-
Great stuffs really. But it does support only classification and object detection with YoloV5. Any chance it will support instance segmentation as this is where most lenghty latency come from.
Than…
-
cc @ChristianMeyndt
NeuralMagic is basically a tool for analyzing a neural net model, and identifying a modified sparse topology that is much smaller and faster. It operates as a second training p…
-
Do you support a local path to the model?
-
I pull the [yolov5 repo](https://github.com/neuralmagic/yolov5) and download the coco dataset to ran the following command
The recipe download from [here](https://github.com/neuralmagic/sparseml/tre…
-