highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-26 20:51:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

ml/backend/ggml: use default CUDA compression mode (#10314)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-04-16 22:54:20 -04:00
committed by GitHub
parent dc264be6ff
commit 09bb2e30f6
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

@@ -24,7 +24,7 @@ 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 none)
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]+"))