cuda: remove compression for better compatibility (#12259)
release / setup-environment (push) Has been cancelled
release / windows-depends (amd64, -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma", https:/… (push) Has been cancelled
release / windows-depends (amd64, ["cudart" "nvcc" "cublas" "cublas_dev" "crt" "nvvm" "nvptxcompiler"], 13.0, , https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe, windows, CUDA 13, cuda_v13) (push) Has been cancelled
release / windows-depends (amd64, ["cudart" "nvcc" "cublas" "cublas_dev"], 12.8, , https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_571.96_windows.exe, windows, CUDA 12, cuda_v12) (push) Has been cancelled
release / windows-depends (amd64, windows, CPU) (push) Has been cancelled
release / darwin-build (amd64, darwin) (push) Has been cancelled
release / darwin-build (arm64, darwin) (push) Has been cancelled
release / windows-build (amd64, windows) (push) Has been cancelled
release / windows-build (arm64, windows) (push) Has been cancelled
release / linux-build (amd64, linux, archive) (push) Has been cancelled
release / linux-build (amd64, linux, rocm) (push) Has been cancelled
release / linux-build (arm64, linux, archive) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS , linux) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS FLAVOR=rocm , linux, -rocm) (push) Has been cancelled
release / docker-build-push (arm64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS , linux) (push) Has been cancelled
release / docker-merge-push () (push) Has been cancelled
release / docker-merge-push (-rocm) (push) Has been cancelled
release / trigger (push) Has been cancelled

This retains compatibility with driver 531 and up at the trade-off of space.
This commit is contained in:
Daniel Hiltgen
2025-09-12 07:59:14 -07:00
committed by GitHub
parent 26214125e8
commit e4ce68311a
+1 -1
View File
@@ -25,7 +25,7 @@ set(GGML_LLAMAFILE ON)
set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128)
set(GGML_CUDA_GRAPHS ON)
set(GGML_CUDA_FA ON)
set(GGML_CUDA_COMPRESSION_MODE size)
set(GGML_CUDA_COMPRESSION_MODE default)
if((CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_OSX_ARCHITECTURES MATCHES "arm64")
OR (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm|aarch64|ARM64|ARMv[0-9]+"))