diff --git a/docs/build.md b/docs/build.md
index d66f95c53..f794d490b 100644
--- a/docs/build.md
+++ b/docs/build.md
@@ -300,7 +300,6 @@ The following compilation options are also available to tweak performance:
 |-------------------------------|------------------------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | GGML_CUDA_FORCE_MMQ           | Boolean                | false   | Force the use of custom matrix multiplication kernels for quantized models instead of FP16 cuBLAS even if there is no int8 tensor core implementation available (affects V100, CDNA and RDNA3+). MMQ kernels are enabled by default on GPUs with int8 tensor core support. With MMQ force enabled, speed for large batch sizes will be worse but VRAM consumption will be lower. |
 | GGML_CUDA_FORCE_CUBLAS        | Boolean                | false   | Force the use of FP16 cuBLAS instead of custom matrix multiplication kernels for quantized models. There may be issues with numerical overflows (except for V100, CDNA and RDNA4 which use FP32 compute type by default) and memory use will be higher. Prompt processing may become faster on recent datacenter GPUs (the custom kernels were tuned primarily for RTX 3000/4000).   |
-| GGML_CUDA_PEER_MAX_BATCH_SIZE | Positive integer       | 128     | Maximum batch size for which to enable peer access between multiple GPUs. Peer access requires either Linux or NVLink. When using NVLink enabling peer access for larger batch sizes is potentially beneficial.                                                                                                                                                                  |
 | GGML_CUDA_FA_ALL_QUANTS       | Boolean                | false   | Compile support for all KV cache quantization type (combinations) for the FlashAttention CUDA kernels. More fine-grained control over KV cache size but compilation takes much longer.                                                                                                                                                                                           |
 
 ## MUSA
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)