Disable CUDA host buffers on integrated GPUs (llama/16308)

diff --git a/src/ggml-cuda/ggml-cuda.cu b/src/ggml-cuda/ggml-cuda.cu
index 26e72bbc2b94209da7a71484302afde3368474f1..fb691528b7de48ee686747e85ea34bca5c47f902 100644 (file)
--- a/src/ggml-cuda/ggml-cuda.cu
+++ b/src/ggml-cuda/ggml-cuda.cu
@@ -231,7 +231,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
 
         info.default_tensor_split[id] = total_vram;
         total_vram += prop.totalGlobalMem;
-        info.devices[id].integrated = prop.integrated;
+        info.devices[id].integrated = false; // Temporarily disabled due to issues with corrupted output (e.g. #15034)
         info.devices[id].nsm        = prop.multiProcessorCount;
         info.devices[id].smpb       = prop.sharedMemPerBlock;
         info.devices[id].warp_size  = prop.warpSize;