Update comment for AdamW implementation reference. (#4604)

Co-authored-by: Will Findley <findley@gmail.com>

README.md

@@ -133,6 +133,7 @@ as the main playground for developing new features for the [ggml](https://github
 - [withcatai/catai](https://github.com/withcatai/catai)
 - [semperai/amica](https://github.com/semperai/amica)
 - [psugihara/FreeChat](https://github.com/psugihara/FreeChat)
+- [ptsochantaris/emeltal](https://github.com/ptsochantaris/emeltal)
 
 ---
 

ggml-cuda.cu

@@ -102,6 +102,7 @@
 #include <cuda_fp16.h>
 
 #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

ggml.c

@@ -17456,9 +17456,9 @@ static void ggml_opt_acc_grad(int np, struct ggml_tensor * const ps[], float * g
 }
 
 //
-// ADAM
+// Using AdamW - ref: https://arxiv.org/pdf/1711.05101v3.pdf
 //
-//   ref: https://arxiv.org/pdf/1412.6980.pdf
+// (Original Adam - ref: https://arxiv.org/pdf/1412.6980.pdf)
 //
 
 static enum ggml_opt_result ggml_opt_adam(