Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177)

Browse Source 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët
2026-09-04 10:22:01 +03:00
committed by GitHub
parent a529af96e2
commit 24f5bf8a41
4 changed files with 0 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/CMakeLists.txt
-2
View File
@@ -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)
ggml/src/ggml-cuda/CMakeLists.txt
-2
View File
@@ -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()
ggml/src/ggml-musa/CMakeLists.txt
-1
View File
@@ -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)