Browse Source
ml/backend/ggml: use default CUDA compression mode (#10314)
mxyng/llama4
v0.6.6-rc2
Jeffrey Morgan
1 year ago
committed by
GitHub
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with
1 additions and
1 deletions
-
CMakeLists.txt
|
|
@ -24,7 +24,7 @@ set(GGML_LLAMAFILE ON) |
|
|
set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128) |
|
|
set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128) |
|
|
set(GGML_CUDA_GRAPHS ON) |
|
|
set(GGML_CUDA_GRAPHS ON) |
|
|
set(GGML_CUDA_FA ON) |
|
|
set(GGML_CUDA_FA ON) |
|
|
set(GGML_CUDA_COMPRESSION_MODE none) |
|
|
set(GGML_CUDA_COMPRESSION_MODE default) |
|
|
|
|
|
|
|
|
if((CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_OSX_ARCHITECTURES MATCHES "arm64") |
|
|
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]+")) |
|
|
OR (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm|aarch64|ARM64|ARMv[0-9]+")) |
|
|
|
