Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
cuda: leverage JIT for smaller footprint (#11635)
Daniel Hiltgendc5a645434f0
diff --git a/CMakePresets.json b/CMakePresets.jsonindex ab2cfe9d6..95ec0d799 100644--- a/CMakePresets.json+++ b/CMakePresets.json@@ -22,7 +22,7 @@"name": "CUDA 12","inherits": [ "CUDA" ],"cacheVariables": {- "CMAKE_CUDA_ARCHITECTURES": "50;60;61;70;75;80;86;87;89;90;90a;120",+ "CMAKE_CUDA_ARCHITECTURES": "50-virtual;60-virtual;61-virtual;70-virtual;75-virtual;80-virtual;86-virtual;89-virtual;90-virtual;90a-virtual;100-virtual;120-virtual","CMAKE_CUDA_FLAGS": "-Wno-deprecated-gpu-targets -t 2"}},@@ -30,14 +30,14 @@"name": "JetPack 5","inherits": [ "CUDA" ],"cacheVariables": {- "CMAKE_CUDA_ARCHITECTURES": "72;87"+ "CMAKE_CUDA_ARCHITECTURES": "72-virtual;87-virtual"}},{"name": "JetPack 6","inherits": [ "CUDA" ],"cacheVariables": {- "CMAKE_CUDA_ARCHITECTURES": "87"+ "CMAKE_CUDA_ARCHITECTURES": "87-virtual"}},{