-
Thanks for sharing the repo . It is really helpful.
I'm exploring ways to do the optimization on GPU. I know its not presently supported. Could you share some approach or references to implement th…
-
### Feature request / 功能建议
The current Dataloader implementation in this repository is underperforming due to a lack of efficient parallelization. This often results in the CPU handling data preproc…
-
**Describe the bug**
Failed to run Olive on gpu-cuda.
**To Reproduce**
Download https://huggingface.co/mistralai/Mistral-7B-v0.1/tree/main to folder: D:\windowsAI\HFModel\Mistral-7B-v01
Follow r…
-
**NVIDIA cuOpt** (cuda Optimization)
NVIDIA cuOpt es una biblioteca optimizada basada en GPU diseñada para resolver problemas de optimización en tiempo real. Está especialmente enfocada en problema…
-
# A list of GPUs has been tested by the following Kernel, it's part of our opensource CFD framwork [XFLUIDS](https://github.com/XFluids/XFluids):
## llvm-16.0.6 is implemented on A100, amd Rocm-5.4.1…
-
A low resolution pre-pass will collect distance information before running, which is used with the full resolution render.
-
I am trying to optimize the current detection model which takes around 400 ms per frame (1080i). The goal is to reach realtime detection using multiple GPU/ Servers. I work with specific images in wh…
-
From Simon Jenni on the google group:
```quote
Running MCore e.g. like this:
MCore \
--population m_run01/population_01.population \
--refine_imagewarp 4x4 \
--refine_particles \
--refine_s…
-
I use --model-control-mode explicit to start the trtion server. After I load the tensorrt model into 2 instances, while sending requests to the model, I modify the number of instances in the configura…
-
It seems that this version runs out of GPU memory more easily compared to the previous one. With the same quality and quantity of photos, the previous version could complete the training (30,000 steps…