NeoCoreTechs - New Core Technologies

Cuda 12

1

Howdy, I am on to Cuda 12, and more fun awaits. ``` From Stack overflow: CUDA 12.0 [dropped support](https://forums.developer.nvidia.com/t/cuda-12-0-still-support-for-texture-reference-support-for-pascal-architecture-warp-synchronous-programming/237284/1) for legacy texture references. Therefore, any code that uses legacy texture...

Cuda 11.4 Jetson Orin Nano failures

9

Greetings, thanks for all the hard work. I got latest JCuda to build on Orin Nano via commenting out breakages. Forked repository at [github.com/neocoretechs/jcuda-1](https://github.com/neocoretechs/jcuda-1)

yolov8s conversion results in 'failed to submit!' on inference.

5

After conversion of yolov8s from ONNX without any errors being reported and using same format as previous yolov5s (which is working), I get this fault on inference after successful load...

Cmake fails on Ubuntu 20

1

uname -a: Linux braincoral 5.4.0-177-generic #197-Ubuntu SMP Thu Mar 28 22:45:47 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux Cmake begins failing when producing C API when following build instructions here: https://www.tensorflow.org/lite/guide/build_cmake...

Vanishing Gradient at ~7-10k tokens multiple models/platforms

2

Using the JVM with this cmdl: java -server -Xmx26g --enable-preview --add-modules jdk.incubator.vector -jar llama3.jar --model Llama-3.2-3B-Instruct-Q8_0.gguf --chat -n 75000 --temperature 0 under JDK 25 Graalvm EA Win11 Ryzen 7 32...

IndexOutOfBoundsException on working code after integrating new working code that used ByteBuffer instead of MemorySegment

7

IndexOutOfBoundsException after integrating code from https://github.com/mukel/qwen2.svm.java into Llama3.java. Code which worked with ByteBuffer now failing on MemorySegment. Failure occurs under Java 25 GraalVM vector extensions incubator under both windows 11...