mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-02-06 16:40:34 +01:00
5245729e33
With robustbufferaccess disabled, this shader was showing OOB stores. There is a bounds check in the code, but the workgrouop dimensions were reversed vs CUDA and it was running the wrong number of threads. So fix the workgroup dimensions and disable robustness for this pipeline. |
||
|---|---|---|
| .. | ||
| cmake | ||
| vulkan-shaders | ||
| CMakeLists.txt | ||
| ggml-vulkan.cpp | ||