diff --git a/ggml/CMakeLists.txt b/ggml/CMakeLists.txt
index 0ac2b15c4..634e18c54 100644
--- a/ggml/CMakeLists.txt
+++ b/ggml/CMakeLists.txt
@@ -200,8 +200,6 @@ option(GGML_CUDA                            "ggml: use CUDA"
 option(GGML_MUSA                            "ggml: use MUSA"                                  OFF)
 option(GGML_CUDA_FORCE_MMQ                  "ggml: use mmq kernels instead of cuBLAS"         OFF)
 option(GGML_CUDA_FORCE_CUBLAS               "ggml: always use cuBLAS instead of mmq kernels"  OFF)
-set   (GGML_CUDA_PEER_MAX_BATCH_SIZE "128" CACHE STRING
-                                            "ggml: max. batch size for using peer access")
 option(GGML_CUDA_NO_PEER_COPY               "ggml: do not use peer to peer copies"            OFF)
 option(GGML_CUDA_NO_VMM                     "ggml: do not try to use CUDA VMM"                OFF)
 option(GGML_CUDA_FA                         "ggml: compile ggml FlashAttention CUDA kernels"  ON)
diff --git a/ggml/src/ggml-cuda/CMakeLists.txt b/ggml/src/ggml-cuda/CMakeLists.txt
index d3953eee9..10828ad81 100644
--- a/ggml/src/ggml-cuda/CMakeLists.txt
+++ b/ggml/src/ggml-cuda/CMakeLists.txt
@@ -129,8 +129,6 @@ if (CUDAToolkit_FOUND)
                              ${GGML_SOURCES_CUDA}
                             )
 
-    add_compile_definitions(GGML_CUDA_PEER_MAX_BATCH_SIZE=${GGML_CUDA_PEER_MAX_BATCH_SIZE})
-
     if (GGML_CUDA_GRAPHS)
         add_compile_definitions(GGML_CUDA_USE_GRAPHS)
     endif()
diff --git a/ggml/src/ggml-musa/CMakeLists.txt b/ggml/src/ggml-musa/CMakeLists.txt
index cc53c812c..faf979033 100644
--- a/ggml/src/ggml-musa/CMakeLists.txt
+++ b/ggml/src/ggml-musa/CMakeLists.txt
@@ -75,7 +75,6 @@ if (MUSAToolkit_FOUND)
     endif()
 
     add_compile_definitions(GGML_USE_MUSA)
-    add_compile_definitions(GGML_CUDA_PEER_MAX_BATCH_SIZE=${GGML_CUDA_PEER_MAX_BATCH_SIZE})
 
     if (GGML_MUSA_GRAPHS)
         add_compile_definitions(GGML_MUSA_GRAPHS)