Skip to content

Fix Metal Support #95

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jun 10, 2023
Merged

Fix Metal Support #95

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2112523
Update llama.o and common.o to use build dir
Jun 10, 2023
26af152
Update Metal Example to work correctly
Jun 10, 2023
678de33
Update test to use CGO_LDFLAGS
Jun 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,6 +145,7 @@ endif

ifeq ($(BUILD_TYPE),metal)
EXTRA_LIBS=
CGO_LDFLAGS+="-framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🤦 feeling guilty, good catch!

CMAKE_ARGS+=-DLLAMA_METAL=ON
EXTRA_TARGETS+=llama.cpp/ggml-metal.o
endif
Expand All @@ -163,6 +164,7 @@ $(info I UNAME_P: $(UNAME_P))
$(info I UNAME_M: $(UNAME_M))
$(info I CFLAGS: $(CFLAGS))
$(info I CXXFLAGS: $(CXXFLAGS))
$(info I CGO_LDFLAGS: $(CGO_LDFLAGS))
$(info I LDFLAGS: $(LDFLAGS))
$(info I BUILD_TYPE: $(BUILD_TYPE))
$(info I CMAKE_ARGS: $(CMAKE_ARGS))
Expand Down Expand Up @@ -191,10 +193,10 @@ llama.cpp/k_quants.o: llama.cpp/ggml.o
cd build && cp -rf CMakeFiles/ggml.dir/k_quants.c.o ../llama.cpp/k_quants.o

llama.cpp/llama.o:
$(MAKE) -C llama.cpp llama.o
cd build && make llama.o && cp -rf CMakeFiles/llama.dir/llama.cpp.o ../llama.cpp/llama.o

llama.cpp/common.o:
$(MAKE) -C llama.cpp common.o
cd build && make common && cp -rf examples/CMakeFiles/common.dir/common.cpp.o ../llama.cpp/common.o

binding.o: llama.cpp/ggml.o llama.cpp/llama.o llama.cpp/common.o
$(CXX) $(CXXFLAGS) -I./llama.cpp -I./llama.cpp/examples binding.cpp -o binding.o -c $(LDFLAGS)
Expand All @@ -208,4 +210,4 @@ clean:
rm -rf build

test: libbinding.a
@C_INCLUDE_PATH=${INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} go test -v ./...
@C_INCLUDE_PATH=${INCLUDE_PATH} CGO_LDFLAGS=${CGO_LDFLAGS} LIBRARY_PATH=${LIBRARY_PATH} go test -v ./...
4 changes: 3 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,9 @@ ggml_opencl: device FP16 support: true

```
BUILD_TYPE=metal make libbinding.a
CGO_LDFLAGS="-framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders" LIBRARY_PATH=$PWD C_INCLUDE_PATH=$PWD go run ./examples -m "/model/path/here" -t 14
CGO_LDFLAGS="-framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders" LIBRARY_PATH=$PWD C_INCLUDE_PATH=$PWD go build ./examples/main.go
cp build/bin/ggml-metal.metal .
./main -m "/model/path/here" -t 1 -ngl 1
```

Enjoy!
Expand Down
8 changes: 5 additions & 3 deletions examples/main.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,15 +13,17 @@ import (
)

var (
threads = 4
tokens = 128
threads = 4
tokens = 128
gpulayers = 0
)

func main() {
var model string

flags := flag.NewFlagSet(os.Args[0], flag.ExitOnError)
flags.StringVar(&model, "m", "./models/7B/ggml-model-q4_0.bin", "path to q4_0.bin model file to load")
flags.IntVar(&gpulayers, "ngl", 0, "Number of GPU layers to use")
flags.IntVar(&threads, "t", runtime.NumCPU(), "number of threads to use during computation")
flags.IntVar(&tokens, "n", 512, "number of tokens to predict")

Expand All @@ -30,7 +32,7 @@ func main() {
fmt.Printf("Parsing program arguments failed: %s", err)
os.Exit(1)
}
l, err := llama.New(model, llama.EnableF16Memory, llama.SetContext(128), llama.EnableEmbeddings)
l, err := llama.New(model, llama.EnableF16Memory, llama.SetContext(128), llama.EnableEmbeddings, llama.SetGPULayers(gpulayers))
if err != nil {
fmt.Println("Loading the model failed:", err.Error())
os.Exit(1)
Expand Down