Engage!

1 files changed, 23 insertions, 0 deletions

diff --git a/llama.cpp/ggml/src/ggml-cuda/vendors/cuda.h b/llama.cpp/ggml/src/ggml-cuda/vendors/cuda.h
new file mode 100644
index 0000000..ba032cf
--- /dev/null
+++ b/llama.cpp/ggml/src/ggml-cuda/vendors/cuda.h
@@ -0,0 +1,23 @@
+#pragma once
+
+#include <cuda_runtime.h>
+#include <cuda.h>
+#include <cublas_v2.h>
+#include <cuda_bf16.h>
+#include <cuda_fp16.h>
+
+#if CUDART_VERSION >= 12050
+#include <cuda_fp8.h>
+#endif // CUDART_VERSION >= 12050
+
+#if CUDART_VERSION >= 12080
+#include <cuda_fp4.h>
+#endif // CUDART_VERSION >= 12080
+
+#if CUDART_VERSION < 11020
+#define CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED
+#define CUBLAS_TF32_TENSOR_OP_MATH CUBLAS_TENSOR_OP_MATH
+#define CUBLAS_COMPUTE_16F CUDA_R_16F
+#define CUBLAS_COMPUTE_32F CUDA_R_32F
+#define cublasComputeType_t cudaDataType_t
+#endif // CUDART_VERSION < 11020