mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda: remove compression for better compatibility (#12259)

Browse Source 
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 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CMakeLists.txt
View File

@@ -25,7 +25,7 @@ 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 size) 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]+"))