mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-28 06:25:00 +00:00
feat: llama.cpp gRPC C++ backend (#1170)
* wip: llama.cpp c++ gRPC server Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * make it work, attach it to the build process Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * update deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: add protobuf dep Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * try fix protobuf on cmake * cmake: workarounds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add packages * cmake: use fixed version of grpc Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * cmake(grpc): install locally * install grpc Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * install required deps for grpc on debian bullseye Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * debug * Fixups * no need to install cmake manually Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: fixup macOS * use brew whenever possible Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * macOS fixups * debug * fix container build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * workaround * try mac https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def * Disable temp. arm64 docker image builds --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
8034ed3473
commit
128694213f
10 changed files with 1145 additions and 16 deletions
26
Makefile
26
Makefile
|
@ -8,6 +8,8 @@ GOLLAMA_VERSION?=1676dcd7a139b6cdfbaea5fd67f46dc25d9d8bcf
|
|||
|
||||
GOLLAMA_STABLE_VERSION?=50cee7712066d9e38306eccadcfbb44ea87df4b7
|
||||
|
||||
CPPLLAMA_VERSION?=24ba3d829e31a6eda3fa1723f692608c2fa3adda
|
||||
|
||||
# gpt4all version
|
||||
GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
|
||||
GPT4ALL_VERSION?=27a8b020c36b0df8f8b82a252d261cda47cf44b8
|
||||
|
@ -120,7 +122,7 @@ ifeq ($(findstring tts,$(GO_TAGS)),tts)
|
|||
OPTIONAL_GRPC+=backend-assets/grpc/piper
|
||||
endif
|
||||
|
||||
GRPC_BACKENDS?=backend-assets/grpc/langchain-huggingface backend-assets/grpc/falcon-ggml backend-assets/grpc/bert-embeddings backend-assets/grpc/falcon backend-assets/grpc/bloomz backend-assets/grpc/llama backend-assets/grpc/llama-stable backend-assets/grpc/gpt4all backend-assets/grpc/dolly backend-assets/grpc/gpt2 backend-assets/grpc/gptj backend-assets/grpc/gptneox backend-assets/grpc/mpt backend-assets/grpc/replit backend-assets/grpc/starcoder backend-assets/grpc/rwkv backend-assets/grpc/whisper $(OPTIONAL_GRPC)
|
||||
GRPC_BACKENDS?=backend-assets/grpc/langchain-huggingface backend-assets/grpc/falcon-ggml backend-assets/grpc/bert-embeddings backend-assets/grpc/falcon backend-assets/grpc/bloomz backend-assets/grpc/llama backend-assets/grpc/llama-cpp backend-assets/grpc/llama-stable backend-assets/grpc/gpt4all backend-assets/grpc/dolly backend-assets/grpc/gpt2 backend-assets/grpc/gptj backend-assets/grpc/gptneox backend-assets/grpc/mpt backend-assets/grpc/replit backend-assets/grpc/starcoder backend-assets/grpc/rwkv backend-assets/grpc/whisper $(OPTIONAL_GRPC)
|
||||
|
||||
.PHONY: all test build vendor
|
||||
|
||||
|
@ -223,7 +225,7 @@ go-llama/libbinding.a: go-llama
|
|||
go-llama-stable/libbinding.a: go-llama-stable
|
||||
$(MAKE) -C go-llama-stable BUILD_TYPE=$(STABLE_BUILD_TYPE) libbinding.a
|
||||
|
||||
go-piper/libpiper_binding.a:
|
||||
go-piper/libpiper_binding.a: go-piper
|
||||
$(MAKE) -C go-piper libpiper_binding.a example/main
|
||||
|
||||
get-sources: go-llama go-llama-stable go-ggllm go-ggml-transformers gpt4all go-piper go-rwkv whisper.cpp go-bert bloomz go-stable-diffusion
|
||||
|
@ -280,6 +282,7 @@ clean: ## Remove build related file
|
|||
rm -rf ./go-ggllm
|
||||
rm -rf $(BINARY_NAME)
|
||||
rm -rf release/
|
||||
$(MAKE) -C backend/cpp/llama clean
|
||||
|
||||
## Build:
|
||||
|
||||
|
@ -395,6 +398,16 @@ ifeq ($(BUILD_TYPE),metal)
|
|||
cp go-llama/build/bin/ggml-metal.metal backend-assets/grpc/
|
||||
endif
|
||||
|
||||
backend/cpp/llama/grpc-server:
|
||||
LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
|
||||
|
||||
backend-assets/grpc/llama-cpp: backend-assets/grpc backend/cpp/llama/grpc-server
|
||||
cp -rfv backend/cpp/llama/grpc-server backend-assets/grpc/llama-cpp
|
||||
# TODO: every binary should have its own folder instead, so can have different metal implementations
|
||||
ifeq ($(BUILD_TYPE),metal)
|
||||
cp backend/cpp/llama/llama.cpp/build/bin/ggml-metal.metal backend-assets/grpc/
|
||||
endif
|
||||
|
||||
backend-assets/grpc/llama-stable: backend-assets/grpc go-llama-stable/libbinding.a
|
||||
$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/go-llama-stable
|
||||
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-llama-stable LIBRARY_PATH=$(shell pwd)/go-llama \
|
||||
|
@ -451,9 +464,12 @@ backend-assets/grpc/bert-embeddings: backend-assets/grpc go-bert/libgobert.a
|
|||
backend-assets/grpc/langchain-huggingface: backend-assets/grpc
|
||||
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/langchain-huggingface ./cmd/grpc/langchain-huggingface/
|
||||
|
||||
backend-assets/grpc/stablediffusion: backend-assets/grpc go-stable-diffusion/libstablediffusion.a
|
||||
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-stable-diffusion/ LIBRARY_PATH=$(shell pwd)/go-stable-diffusion/ \
|
||||
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion ./cmd/grpc/stablediffusion/
|
||||
backend-assets/grpc/stablediffusion: backend-assets/grpc
|
||||
if [ ! -f backend-assets/grpc/stablediffusion ]; then \
|
||||
$(MAKE) go-stable-diffusion/libstablediffusion.a; \
|
||||
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-stable-diffusion/ LIBRARY_PATH=$(shell pwd)/go-stable-diffusion/ \
|
||||
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion ./cmd/grpc/stablediffusion/; \
|
||||
fi
|
||||
|
||||
backend-assets/grpc/piper: backend-assets/grpc backend-assets/espeak-ng-data go-piper/libpiper_binding.a
|
||||
CGO_LDFLAGS="$(CGO_LDFLAGS)" LIBRARY_PATH=$(shell pwd)/go-piper \
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue