Merge remote-tracking branch 'upstream/concedo'

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "kompute"]
-	path = kompute
-	url = https://github.com/nomic-ai/kompute.git

CMakeLists.txt

@@ -27,8 +27,6 @@ set(LLAMA_SANITIZE_THREAD OFF)
 set(LLAMA_SANITIZE_ADDRESS OFF)
 set(LLAMA_SANITIZE_UNDEFINED OFF)
 
-option(MAKE_MISC_FILES              "MAKE_MISC_FILES"                                       OFF)
-
 # instruction set specific
 option(LLAMA_AVX                        "llama: enable AVX"                                     ON)
 option(LLAMA_AVX2                       "llama: enable AVX2"                                    ON)
@@ -467,18 +465,3 @@ if (LLAMA_HIPBLAS)
     target_compile_features(${TARGET} PRIVATE cxx_std_11)
 endif()
 
-
-if (MAKE_MISC_FILES)
-add_subdirectory(common)
-add_library(llama
-        llama.cpp
-        llama.h
-        )
-target_include_directories(llama PUBLIC .)
-target_compile_features(llama PUBLIC cxx_std_11) # don't bump
-target_link_libraries(llama PRIVATE
-    ggml
-    ${LLAMA_EXTRA_LIBS}
-    )
-add_subdirectory(examples)
-endif()

Makefile

@@ -143,7 +143,7 @@ endif
 # it is recommended to use the CMAKE file to build for cublas if you can - will likely work better
 ifdef LLAMA_CUBLAS
 	CUBLAS_FLAGS = -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
-	CUBLASLD_FLAGS = -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
+	CUBLASLD_FLAGS = -lcuda -lcublas -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
 	CUBLAS_OBJS = ggml-cuda.o ggml_v3-cuda.o ggml_v2-cuda.o ggml_v2-cuda-legacy.o
 	NVCC      = nvcc
 	NVCCFLAGS = --forward-unknown-to-host-compiler -use_fast_math