ollama/llm/llama.cpp/generate_darwin_arm64.go

package llm

//go:generate git submodule init
//go:generate git submodule update --force ggml
//go:generate git -C ggml apply ../ggml_patch/0001-add-detokenize-endpoint.patch
//go:generate git -C ggml apply ../ggml_patch/0002-34B-model-support.patch
//go:generate cmake -S ggml -B ggml/build/gpu -DLLAMA_METAL=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DCMAKE_SYSTEM_PROCESSOR=arm64 -DCMAKE_OSX_ARCHITECTURES=arm64
//go:generate cmake --build ggml/build/gpu --target server --config Release
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`package llm`

			`//go:generate git submodule init`
			`//go:generate git submodule update --force ggml`
			`//go:generate git -C ggml apply ../ggml_patch/0001-add-detokenize-endpoint.patch`
			`//go:generate git -C ggml apply ../ggml_patch/0002-34B-model-support.patch`
generate binary dependencies based on GOARCH on macos (#459) 2023-09-05 16:53:57 +00:00			`//go:generate cmake -S ggml -B ggml/build/gpu -DLLAMA_METAL=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DCMAKE_SYSTEM_PROCESSOR=arm64 -DCMAKE_OSX_ARCHITECTURES=arm64`
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`//go:generate cmake --build ggml/build/gpu --target server --config Release`