Skip to content

GitLab

Unverified Commit 09bb2e30 authored by Jeffrey Morgan's avatar Jeffrey Morgan Committed by GitHub
Browse files

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

parent dc264be6
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
CMakeLists.txt
View file @ 09bb2e30
...@@ -24,7 +24,7 @@ set(GGML_LLAMAFILE ON) ...@@ -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]+"))
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment