Fix talk-llama build after ggml sync (commit 5feb0dffbae5).

[przemoc]

sed -i 's,GGML_BACKEND_CUDA,GGML_BACKEND_GPU,g' examples/talk-llama/llama.cpp

[jasontitus]

Getting errors and a failed build with current checkout on a 'make clean' and 'WHISPER_COREML=1 make talk-llama'

I whisper.cpp build info:
I UNAME_S: Darwin
I UNAME_P: arm
I UNAME_M: arm64
I CFLAGS: -I. -O3 -DNDEBUG -std=c11 -fPIC -D_XOPEN_SOURCE=600 -pthread -DGGML_USE_ACCELERATE
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -pthread -DWHISPER_USE_COREML
I LDFLAGS: -framework Accelerate -framework Foundation -framework CoreML
I CC: Apple clang version 14.0.3 (clang-1403.0.22.14.1)
I CXX: Apple clang version 14.0.3 (clang-1403.0.22.14.1)

c++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -pthread -DWHISPER_USE_COREML examples/talk-llama/talk-llama.cpp examples/talk-llama/llama.cpp examples/common.cpp examples/common-ggml.cpp examples/common-sdl.cpp ggml.o whisper.o whisper-encoder.o whisper-encoder-impl.o -o talk-llama sdl2-config --cflags --libs -framework Accelerate -framework Foundation -framework CoreML
In file included from examples/talk-llama/llama.cpp:1:
examples/talk-llama/llama-util.h:189:63: error: use of undeclared identifier 'MADV_WILLNEED'
if (madvise(addr, std::min(file->size, prefetch), MADV_WILLNEED)) {
^
examples/talk-llama/llama-util.h:316:38: error: use of undeclared identifier 'RLIMIT_MEMLOCK'
if (suggest && getrlimit(RLIMIT_MEMLOCK, &lock_limit))
^
2 errors generated.
make: *** [talk-llama] Error 1

[przemoc]

@jasontitus, not sure if you got notification from #1062, so please go there.