Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

cuda: remove compression for better compatibility (#12259)

Daniel Hiltgene4ce68311a64
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 7cce5e4b1..198fcdeb9 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -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]+"))