-
This is to call the efficiency improvement for LightGBM, include but not limited to:
- Tree learning algorithm acceleration
- I/O related, like dataset loading and model saving
- Inference speed im…
-
Hi,
I have read the "examples\NPU compilation tutorial.ipynb" about graph mode and eager mode, which helped me a lot.
I was wondering if I could use graph mode in LLM inference to reduce the weights…
-
### 📚 The doc issue
In the Inference (Energon-AI) [Demo](https://github.com/hpcaitech/ColossalAI#GPT-3-Inference), what is the hardware used in th Energon-AI inference acceleration ? Can you show…
-
- I want to keep exo 100% python if possible
- Would like to compile swift or objc inference code in tinygrad
- The deliverable here is a merged PR in tinygrad and a small demonstration in exo of ho…
-
### Search before asking
- [X] I have searched the HUB [issues](https://github.com/ultralytics/hub/issues) and found no similar bug report.
### HUB Component
Datasets
### Bug
I got time out erro…
-
Hi
This is general question about deep learning inference acceleration with coriander. TF XLA good idea for inference optimization but limited available CUDA. And NVIDIA also release TensorRT as in…
-
![Screenshot_20240808_204712](https://github.com/user-attachments/assets/a0546fd7-2e52-44ad-9d65-9d8e3c385dd0)
how can i set the sd model? It is null?
without i get this error:
```
find mo…
-
- [x] PyTorch Train tutorial
- [x] PyTorch Inference
- [x] runtime acceleration with openvino
- [x] runtime acceleration with onnx-runtime
- [x] quantization with INC
- [x] quant…
-
Since there many ops were using C++ implemented as well as CUDA. Would it be useful to make it trace and inference in libtorch?
I believe it would make much more speed acceleration using libtorch a…
-
We propose [MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models](https://arxiv.org/pdf/2405.13053). Our proposed MeteoRA (Multiple-Tasks embedded LoRA) is a scalable and efficient framewor…