-
We should start with `do concurrent`, using the NVPTX LLVM backend, there is nice documentation and tutorial here: https://llvm.org/docs/NVPTXUsage.html.
It looks like the steps are:
* manual ke…
-
Hello, I have a problem to use the gpu in open3d 0.18.. To enable GPU support, I build open3d from source and create the Python bindings. Unfortunately I always get an error when importing the library…
-
为什么yolov11 - Segment- opencv 无法跑GPU
-
I want to train with multiple gpu's, besides setting the export header="torchrun --nproc_per_node 4 --nnodes 1 and export CUDA_VISIBLE_DEVICES=4,5,6,7，is there anything else I need to set up? Because …
-
How much graphics memory is required to run this project at least? Can I successfully run the RTX3090 that I currently only have 24G? If not, can certain hyperparameters be modified to successfully ru…
-
Hello,
I am currently using your software on macOS with the Apple M1 Ultra. However, I have noticed that the GPU performance on macOS is not being fully utilized, which significantly impacts overal…
-
### What is the issue?
I had ollama compiled from source and it worked fine. Recently I rebuild it to the last version, and it seems to not use my GPU anymore (it uses a lot of CPU processes, and it …
-
Hi,
I would like to investigate the possibility of using your project as a basis for a simple GPU. The idea is as follows:
1. MSX triggers rendering a frame on the pi using io ports
2. pi rende…
-
### What is the issue?
when I use llama3.2-vision:90b ，the model always response so slow. how can I do?
And the GPU is not fully used. CPU used very high.
it's run on V100*4 = 64G GPU
Is anyone ca…
-
The following TTGIR currently fails with CUDA_ERROR_ILLEGAL_ADDRESS.
- The configuration used for this test case is `{"block_m":16,"block_n":16,"block_k":16,"split_k":1,"num_stages":2,"num_warps":2…