LocalAI/Makefile

536 lines
26 KiB
Makefile
Raw Normal View History

GOCMD=go
GOTEST=$(GOCMD) test
GOVET=$(GOCMD) vet
BINARY_NAME=local-ai
2023-05-04 10:26:59 +00:00
2023-07-04 17:02:02 +00:00
# llama.cpp versions
GOLLAMA_VERSION?=aeba71ee842819da681ea537e78846dc75949ac0
2023-07-04 17:02:02 +00:00
GOLLAMA_STABLE_VERSION?=50cee7712066d9e38306eccadcfbb44ea87df4b7
CPPLLAMA_VERSION?=8a7b2fa528f130631a5f43648481596ab320ed5a
2023-07-04 17:02:02 +00:00
# gpt4all version
GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
GPT4ALL_VERSION?=27a8b020c36b0df8f8b82a252d261cda47cf44b8
2023-07-04 17:02:02 +00:00
# go-ggml-transformers version
GOGGMLTRANSFORMERS_VERSION?=ffb09d7dd71e2cbc6c5d7d05357d230eea6f369a
2023-07-04 17:02:02 +00:00
# go-rwkv version
RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
RWKV_VERSION?=c898cd0f62df8f2a7830e53d1d513bef4f6f792b
2023-07-04 17:02:02 +00:00
# whisper.cpp version
WHISPER_CPP_VERSION?=ec03661b20c7d8b66348c0a439c3386b996b2b72
2023-07-04 17:02:02 +00:00
# bert.cpp version
BERT_VERSION?=6abe312cded14042f6b7c3cd8edf082713334a4d
2023-07-04 17:02:02 +00:00
# go-piper version
PIPER_VERSION?=6e687b16e88f9451c2ece5b8ff3627ecf54c4a68
2023-07-04 17:02:02 +00:00
# stablediffusion version
STABLEDIFFUSION_VERSION?=902db5f066fd137697e3b69d0fa10d4782bd2c2f
2023-07-04 17:02:02 +00:00
export BUILD_TYPE?=
feat(llama.cpp): enable ROCm/HIPBLAS support (#1100) **Description** This PR fixes lack of HIPBLAS support in LocalAI. **Notes for Reviewers** This PR builds on https://github.com/go-skynet/go-llama.cpp/pull/235 to enable ROCm/HIPBLAS support for gguf models running under llama.cpp backend (not the stable ggml one). It can be enabled by using BUILD_TYPE=hipblas. This was tested on a gfx1100 card, but should work for gfx900,gfx1030 and other cards. Card support can be set with AMDGPU_TARGETS environment variable. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> --------- Signed-off-by: 65a <65a@63bit.net>
2023-09-28 19:42:20 +00:00
export STABLE_BUILD_TYPE?=$(BUILD_TYPE)
export CMAKE_ARGS?=
CGO_LDFLAGS?=
CUDA_LIBPATH?=/usr/local/cuda/lib64/
GO_TAGS?=
BUILD_ID?=git
TEST_DIR=/tmp/test
RANDOM := $(shell bash -c 'echo $$RANDOM')
VERSION?=$(shell git describe --always --tags || echo "dev" )
# go tool nm ./local-ai | grep Commit
LD_FLAGS?=
override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Version=$(VERSION)"
override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Commit=$(shell git rev-parse HEAD)"
OPTIONAL_TARGETS?=
OS := $(shell uname -s)
ARCH := $(shell uname -m)
GREEN := $(shell tput -Txterm setaf 2)
YELLOW := $(shell tput -Txterm setaf 3)
WHITE := $(shell tput -Txterm setaf 7)
CYAN := $(shell tput -Txterm setaf 6)
RESET := $(shell tput -Txterm sgr0)
# Default Docker bridge IP
E2E_BRIDGE_IP?=172.17.0.1
ifndef UNAME_S
UNAME_S := $(shell uname -s)
endif
ifeq ($(OS),Darwin)
CGO_LDFLAGS += -lcblas -framework Accelerate
ifeq ($(OSX_SIGNING_IDENTITY),)
OSX_SIGNING_IDENTITY := $(shell security find-identity -v -p codesigning | grep '"' | head -n 1 | sed -E 's/.*"(.*)"/\1/')
endif
# on OSX, if BUILD_TYPE is blank, we should default to use Metal
ifeq ($(BUILD_TYPE),)
BUILD_TYPE=metal
# disable metal if on Darwin and any other value is explicitly passed.
else ifneq ($(BUILD_TYPE),metal)
CMAKE_ARGS+=-DLLAMA_METAL=OFF
endif
endif
ifeq ($(BUILD_TYPE),openblas)
CGO_LDFLAGS+=-lopenblas
export WHISPER_OPENBLAS=1
endif
ifeq ($(BUILD_TYPE),cublas)
CGO_LDFLAGS+=-lcublas -lcudart -L$(CUDA_LIBPATH)
export LLAMA_CUBLAS=1
export WHISPER_CUBLAS=1
endif
feat(llama.cpp): enable ROCm/HIPBLAS support (#1100) **Description** This PR fixes lack of HIPBLAS support in LocalAI. **Notes for Reviewers** This PR builds on https://github.com/go-skynet/go-llama.cpp/pull/235 to enable ROCm/HIPBLAS support for gguf models running under llama.cpp backend (not the stable ggml one). It can be enabled by using BUILD_TYPE=hipblas. This was tested on a gfx1100 card, but should work for gfx900,gfx1030 and other cards. Card support can be set with AMDGPU_TARGETS environment variable. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> --------- Signed-off-by: 65a <65a@63bit.net>
2023-09-28 19:42:20 +00:00
ifeq ($(BUILD_TYPE),hipblas)
ROCM_HOME ?= /opt/rocm
export CXX=$(ROCM_HOME)/llvm/bin/clang++
export CC=$(ROCM_HOME)/llvm/bin/clang
# llama-ggml has no hipblas support, so override it here.
feat(llama.cpp): enable ROCm/HIPBLAS support (#1100) **Description** This PR fixes lack of HIPBLAS support in LocalAI. **Notes for Reviewers** This PR builds on https://github.com/go-skynet/go-llama.cpp/pull/235 to enable ROCm/HIPBLAS support for gguf models running under llama.cpp backend (not the stable ggml one). It can be enabled by using BUILD_TYPE=hipblas. This was tested on a gfx1100 card, but should work for gfx900,gfx1030 and other cards. Card support can be set with AMDGPU_TARGETS environment variable. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> --------- Signed-off-by: 65a <65a@63bit.net>
2023-09-28 19:42:20 +00:00
export STABLE_BUILD_TYPE=
export WHISPER_HIPBLAS=1
feat(llama.cpp): enable ROCm/HIPBLAS support (#1100) **Description** This PR fixes lack of HIPBLAS support in LocalAI. **Notes for Reviewers** This PR builds on https://github.com/go-skynet/go-llama.cpp/pull/235 to enable ROCm/HIPBLAS support for gguf models running under llama.cpp backend (not the stable ggml one). It can be enabled by using BUILD_TYPE=hipblas. This was tested on a gfx1100 card, but should work for gfx900,gfx1030 and other cards. Card support can be set with AMDGPU_TARGETS environment variable. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> --------- Signed-off-by: 65a <65a@63bit.net>
2023-09-28 19:42:20 +00:00
GPU_TARGETS ?= gfx900,gfx90a,gfx1030,gfx1031,gfx1100
AMDGPU_TARGETS ?= "$(GPU_TARGETS)"
CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS="$(AMDGPU_TARGETS)" -DGPU_TARGETS="$(GPU_TARGETS)"
CGO_LDFLAGS += -O3 --rtlib=compiler-rt -unwindlib=libgcc -lhipblas -lrocblas --hip-link
endif
ifeq ($(BUILD_TYPE),metal)
CGO_LDFLAGS+=-framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
export LLAMA_METAL=1
export WHISPER_METAL=1
endif
ifeq ($(BUILD_TYPE),clblas)
CGO_LDFLAGS+=-lOpenCL -lclblast
export WHISPER_CLBLAST=1
endif
2023-05-24 14:42:24 +00:00
# glibc-static or glibc-devel-static required
ifeq ($(STATIC),true)
LD_FLAGS=-linkmode external -extldflags -static
endif
ifeq ($(findstring stablediffusion,$(GO_TAGS)),stablediffusion)
# OPTIONAL_TARGETS+=go-stable-diffusion/libstablediffusion.a
OPTIONAL_GRPC+=backend-assets/grpc/stablediffusion
endif
ifeq ($(findstring tts,$(GO_TAGS)),tts)
# OPTIONAL_TARGETS+=go-piper/libpiper_binding.a
# OPTIONAL_TARGETS+=backend-assets/espeak-ng-data
PIPER_CGO_CXXFLAGS+=-I$(shell pwd)/sources/go-piper/piper/src/cpp -I$(shell pwd)/sources/go-piper/piper/build/fi/include -I$(shell pwd)/sources/go-piper/piper/build/pi/include -I$(shell pwd)/sources/go-piper/piper/build/si/include
PIPER_CGO_LDFLAGS+=-L$(shell pwd)/sources/go-piper/piper/build/fi/lib -L$(shell pwd)/sources/go-piper/piper/build/pi/lib -L$(shell pwd)/sources/go-piper/piper/build/si/lib -lfmt -lspdlog -lucd
OPTIONAL_GRPC+=backend-assets/grpc/piper
endif
ALL_GRPC_BACKENDS=backend-assets/grpc/langchain-huggingface backend-assets/grpc/falcon-ggml backend-assets/grpc/bert-embeddings backend-assets/grpc/llama backend-assets/grpc/llama-cpp backend-assets/grpc/llama-ggml 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?=$(ALL_GRPC_BACKENDS) $(OPTIONAL_GRPC)
# If empty, then we build all
ifeq ($(GRPC_BACKENDS),)
GRPC_BACKENDS=$(ALL_GRPC_BACKENDS)
endif
.PHONY: all test build vendor
all: help
## GPT4ALL
sources/gpt4all:
git clone --recurse-submodules $(GPT4ALL_REPO) sources/gpt4all
cd sources/gpt4all && git checkout -b build $(GPT4ALL_VERSION) && git submodule update --init --recursive --depth 1
## go-piper
sources/go-piper:
git clone --recurse-submodules https://github.com/mudler/go-piper sources/go-piper
cd sources/go-piper && git checkout -b build $(PIPER_VERSION) && git submodule update --init --recursive --depth 1
2023-05-10 13:20:21 +00:00
## BERT embeddings
sources/go-bert:
git clone --recurse-submodules https://github.com/go-skynet/go-bert.cpp sources/go-bert
cd sources/go-bert && git checkout -b build $(BERT_VERSION) && git submodule update --init --recursive --depth 1
2023-05-10 13:20:21 +00:00
## stable diffusion
sources/go-stable-diffusion:
git clone --recurse-submodules https://github.com/mudler/go-stable-diffusion sources/go-stable-diffusion
cd sources/go-stable-diffusion && git checkout -b build $(STABLEDIFFUSION_VERSION) && git submodule update --init --recursive --depth 1
sources/go-stable-diffusion/libstablediffusion.a:
$(MAKE) -C sources/go-stable-diffusion libstablediffusion.a
## RWKV
sources/go-rwkv:
git clone --recurse-submodules $(RWKV_REPO) sources/go-rwkv
cd sources/go-rwkv && git checkout -b build $(RWKV_VERSION) && git submodule update --init --recursive --depth 1
sources/go-rwkv/librwkv.a: sources/go-rwkv
cd sources/go-rwkv && cd rwkv.cpp && cmake . -DRWKV_BUILD_SHARED_LIBRARY=OFF && cmake --build . && cp librwkv.a ..
sources/go-bert/libgobert.a: sources/go-bert
$(MAKE) -C sources/go-bert libgobert.a
2023-05-10 13:20:21 +00:00
backend-assets/gpt4all: sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a
mkdir -p backend-assets/gpt4all
@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.so backend-assets/gpt4all/ || true
@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.dylib backend-assets/gpt4all/ || true
@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.dll backend-assets/gpt4all/ || true
backend-assets/espeak-ng-data: sources/go-piper
mkdir -p backend-assets/espeak-ng-data
$(MAKE) -C sources/go-piper piper.o
@cp -rf sources/go-piper/piper-phonemize/pi/share/espeak-ng-data/. backend-assets/espeak-ng-data
sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a: sources/gpt4all
$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ libgpt4all.a
## CEREBRAS GPT
sources/go-ggml-transformers:
git clone --recurse-submodules https://github.com/go-skynet/go-ggml-transformers.cpp sources/go-ggml-transformers
cd sources/go-ggml-transformers && git checkout -b build $(GOGPT2_VERSION) && git submodule update --init --recursive --depth 1
sources/go-ggml-transformers/libtransformers.a: sources/go-ggml-transformers
$(MAKE) -C sources/go-ggml-transformers BUILD_TYPE=$(BUILD_TYPE) libtransformers.a
sources/whisper.cpp:
git clone https://github.com/ggerganov/whisper.cpp.git sources/whisper.cpp
cd sources/whisper.cpp && git checkout -b build $(WHISPER_CPP_VERSION) && git submodule update --init --recursive --depth 1
2023-05-09 09:43:50 +00:00
sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
cd sources/whisper.cpp && make libwhisper.a
2023-05-09 09:43:50 +00:00
sources/go-llama:
git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp sources/go-llama
cd sources/go-llama && git checkout -b build $(GOLLAMA_VERSION) && git submodule update --init --recursive --depth 1
sources/go-llama-ggml:
git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp sources/go-llama-ggml
cd sources/go-llama-ggml && git checkout -b build $(GOLLAMA_STABLE_VERSION) && git submodule update --init --recursive --depth 1
sources/go-llama/libbinding.a: sources/go-llama
$(MAKE) -C sources/go-llama BUILD_TYPE=$(BUILD_TYPE) libbinding.a
sources/go-llama-ggml/libbinding.a: sources/go-llama-ggml
$(MAKE) -C sources/go-llama-ggml BUILD_TYPE=$(STABLE_BUILD_TYPE) libbinding.a
sources/go-piper/libpiper_binding.a: sources/go-piper
$(MAKE) -C sources/go-piper libpiper_binding.a example/main
backend/cpp/llama/llama.cpp:
$(MAKE) -C backend/cpp/llama llama.cpp
get-sources: backend/cpp/llama/llama.cpp sources/go-llama sources/go-llama-ggml sources/go-ggml-transformers sources/gpt4all sources/go-piper sources/go-rwkv sources/whisper.cpp sources/go-bert sources/go-stable-diffusion
2023-06-26 20:34:03 +00:00
touch $@
replace:
$(GOCMD) mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=$(shell pwd)/sources/gpt4all/gpt4all-bindings/golang
$(GOCMD) mod edit -replace github.com/go-skynet/go-ggml-transformers.cpp=$(shell pwd)/sources/go-ggml-transformers
$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(shell pwd)/sources/go-rwkv
$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp=$(shell pwd)/sources/whisper.cpp
$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp/bindings/go=$(shell pwd)/sources/whisper.cpp/bindings/go
$(GOCMD) mod edit -replace github.com/go-skynet/go-bert.cpp=$(shell pwd)/sources/go-bert
$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(shell pwd)/sources/go-stable-diffusion
$(GOCMD) mod edit -replace github.com/mudler/go-piper=$(shell pwd)/sources/go-piper
2023-06-26 20:34:03 +00:00
prepare-sources: get-sources replace
$(GOCMD) mod download
touch $@
## GENERIC
rebuild: ## Rebuilds the project
2023-07-05 16:24:55 +00:00
$(GOCMD) clean -cache
$(MAKE) -C sources/go-llama clean
$(MAKE) -C sources/go-llama-ggml clean
$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ clean
$(MAKE) -C sources/go-ggml-transformers clean
$(MAKE) -C sources/go-rwkv clean
$(MAKE) -C sources/whisper.cpp clean
$(MAKE) -C sources/go-stable-diffusion clean
$(MAKE) -C sources/go-bert clean
$(MAKE) -C sources/go-piper clean
$(MAKE) build
prepare: prepare-sources $(OPTIONAL_TARGETS)
2023-06-26 20:34:03 +00:00
touch $@
clean: ## Remove build related file
2023-07-05 16:24:55 +00:00
$(GOCMD) clean -cache
rm -f prepare
rm -rf ./sources
rm -rf $(BINARY_NAME)
rm -rf release/
rm -rf ./backend/cpp/grpc/grpc_repo
rm -rf ./backend/cpp/grpc/build
rm -rf ./backend/cpp/grpc/installed_packages
$(MAKE) -C backend/cpp/llama clean
## Build:
build: grpcs prepare ## Build the project
$(info ${GREEN}I local-ai build info:${RESET})
$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
$(info ${GREEN}I LD_FLAGS: ${YELLOW}$(LD_FLAGS)${RESET})
CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./
dist: build
mkdir -p release
cp $(BINARY_NAME) release/$(BINARY_NAME)-$(BUILD_ID)-$(OS)-$(ARCH)
osx-signed: build
codesign --deep --force --sign "$(OSX_SIGNING_IDENTITY)" --entitlements "./Entitlements.plist" "./$(BINARY_NAME)"
## Run
run: prepare ## run local-ai
CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) run ./
test-models/testmodel:
mkdir test-models
mkdir test-dir
feat(conda): conda environments (#1144) * feat(autogptq): add a separate conda environment for autogptq (#1137) **Description** This PR related to #1117 **Notes for Reviewers** Here we lock down the version of the dependencies. Make sure it can be used all the time without failed if the version of dependencies were upgraded. I change the order of importing packages according to the pylint, and no change the logic of code. It should be ok. I will do more investigate on writing some test cases for every backend. I can run the service in my environment, but there is not exist a way to test it. So, I am not confident on it. Add a README.md in the `grpc` root. This is the common commands for creating `conda` environment. And it can be used to the reference file for creating extral gRPC backend document. Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * [Extra backend] Add seperate environment for ttsbark (#1141) **Description** This PR relates to #1117 **Notes for Reviewers** Same to the latest PR: * The code is also changed, but only the order of the import package parts. And some code comments are also added. * Add a configuration of the `conda` environment * Add a simple test case for testing if the service can be startup in current `conda` environment. It is succeed in VSCode, but the it is not out of box on terminal. So, it is hard to say the test case really useful. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): add make target and entrypoints for the dockerfile Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add seperate conda env for diffusers (#1145) **Description** This PR relates to #1117 **Notes for Reviewers** * Add `conda` env `diffusers.yml` * Add Makefile to create it automatically * Add `run.sh` to support running as a extra backend * Also adding it to the main Dockerfile * Add make command in the root Makefile * Testing the server, it can start up under the env Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for vllm (#1148) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server can be started as normal * The test case can be triggered in VSCode * Same to other this kind of PRs, add `vllm.yml` Makefile and add `run.sh` to the main Dockerfile, and command to the main Makefile **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for huggingface (#1146) **Description** This PR is related to #1117 **Notes for Reviewers** * Add conda env `huggingface.yml` * Change the import order, and also remove the no-used packages * Add `run.sh` and `make command` to the main Dockerfile and Makefile * Add test cases for it. It can be triggered and succeed under VSCode Python extension but it is hang by using `python -m unites test_huggingface.py` in the terminal ``` Running tests (unittest): /workspaces/LocalAI/extra/grpc/huggingface Running tests: /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_embedding /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_load_model /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_server_startup ./test_huggingface.py::TestBackendServicer::test_embedding Passed ./test_huggingface.py::TestBackendServicer::test_load_model Passed ./test_huggingface.py::TestBackendServicer::test_server_startup Passed Total number of tests expected to run: 3 Total number of tests run: 3 Total number of tests passed: 3 Total number of tests failed: 0 Total number of tests failed with errors: 0 Total number of tests skipped: 0 Finished running tests! ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add the seperate conda env for VALL-E X (#1147) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server cannot start up ``` (ttsvalle) @Aisuko ➜ /workspaces/LocalAI (feat/vall-e-x) $ /opt/conda/envs/ttsvalle/bin/python /workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py Traceback (most recent call last): File "/workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py", line 14, in <module> from utils.generation import SAMPLE_RATE, generate_audio, preload_models ModuleNotFoundError: No module named 'utils' ``` The installation steps follow https://github.com/Plachtaa/VALL-E-X#-installation below: * Under the `ttsvalle` conda env ``` git clone https://github.com/Plachtaa/VALL-E-X.git cd VALL-E-X pip install -r requirements.txt ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: set image type Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate conda env for exllama (#1149) Add seperate env for exllama Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Setup conda Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set image_type arg Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: prepare only conda env in tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Dockerfile: comment manual pip calls Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * conda: add conda to PATH Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixes * add shebang * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * file perms Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * Install new conda in the worker * Disable GPU tests for now until the worker is back * Rename workflows * debug * Fixup conda install * fixup(wrapper): pass args Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Aisuko <urakiny@gmail.com>
2023-11-04 14:30:32 +00:00
wget -q https://huggingface.co/nnakasato/ggml-model-test/resolve/main/ggml-model-q4.bin -O test-models/testmodel
wget -q https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
wget -q https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin -O test-models/bert
wget -q https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
wget -q https://huggingface.co/mudler/rwkv-4-raven-1.5B-ggml/resolve/main/RWKV-4-Raven-1B5-v11-Eng99%2525-Other1%2525-20230425-ctx4096_Q4_0.bin -O test-models/rwkv
wget -q https://raw.githubusercontent.com/saharNooby/rwkv.cpp/5eb8f09c146ea8124633ab041d9ea0b1f1db4459/rwkv/20B_tokenizer.json -O test-models/rwkv.tokenizer.json
cp tests/models_fixtures/* test-models
prepare-test: grpcs
cp -rf backend-assets api
cp tests/models_fixtures/* test-models
test: prepare test-models/testmodel grpcs
@echo 'Running tests'
export GO_TAGS="tts stablediffusion"
$(MAKE) prepare-test
HUGGINGFACE_GRPC=$(abspath ./)/backend/python/sentencetransformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!gpt4all && !llama && !llama-gguf" --flake-attempts 5 --fail-fast -v -r ./api ./pkg
$(MAKE) test-gpt4all
$(MAKE) test-llama
$(MAKE) test-llama-gguf
$(MAKE) test-tts
$(MAKE) test-stablediffusion
prepare-e2e:
mkdir -p $(TEST_DIR)
cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml
test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin
docker build --build-arg BUILD_GRPC=true --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=11 --build-arg CUDA_MINOR_VERSION=7 --build-arg FFMPEG=true -t localai-tests .
run-e2e-image:
ls -liah $(abspath ./tests/e2e-fixtures)
docker run -p 5390:8080 -e MODELS_PATH=/models -e THREADS=1 -e DEBUG=true -d --rm -v $(TEST_DIR):/models --gpus all --name e2e-tests-$(RANDOM) localai-tests
test-e2e:
@echo 'Running e2e tests'
BUILD_TYPE=$(BUILD_TYPE) \
LOCALAI_API=http://$(E2E_BRIDGE_IP):5390/v1 \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts 5 -v -r ./tests/e2e
teardown-e2e:
rm -rf $(TEST_DIR) || true
docker stop $$(docker ps -q --filter ancestor=localai-tests)
test-gpt4all: prepare-test
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="gpt4all" --flake-attempts 5 -v -r ./api ./pkg
test-llama: prepare-test
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama" --flake-attempts 5 -v -r ./api ./pkg
test-llama-gguf: prepare-test
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama-gguf" --flake-attempts 5 -v -r ./api ./pkg
test-tts: prepare-test
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="tts" --flake-attempts 1 -v -r ./api ./pkg
test-stablediffusion: prepare-test
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="stablediffusion" --flake-attempts 1 -v -r ./api ./pkg
test-container:
docker build --target requirements -t local-ai-test-container .
docker run -ti --rm --entrypoint /bin/bash -ti -v $(abspath ./):/build local-ai-test-container
## Help:
help: ## Show this help.
@echo ''
@echo 'Usage:'
@echo ' ${YELLOW}make${RESET} ${GREEN}<target>${RESET}'
@echo ''
@echo 'Targets:'
@awk 'BEGIN {FS = ":.*?## "} { \
if (/^[a-zA-Z_-]+:.*?##.*$$/) {printf " ${YELLOW}%-20s${GREEN}%s${RESET}\n", $$1, $$2} \
else if (/^## .*$$/) {printf " ${CYAN}%s${RESET}\n", substr($$1,4)} \
}' $(MAKEFILE_LIST)
protogen: protogen-go protogen-python
protogen-go:
protoc -Ibackend/ --go_out=pkg/grpc/proto/ --go_opt=paths=source_relative --go-grpc_out=pkg/grpc/proto/ --go-grpc_opt=paths=source_relative \
backend/backend.proto
protogen-python:
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/sentencetransformers/ --grpc_python_out=backend/python/sentencetransformers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/transformers/ --grpc_python_out=backend/python/transformers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/transformers-musicgen/ --grpc_python_out=backend/python/transformers-musicgen/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/autogptq/ --grpc_python_out=backend/python/autogptq/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/exllama/ --grpc_python_out=backend/python/exllama/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/bark/ --grpc_python_out=backend/python/bark/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/diffusers/ --grpc_python_out=backend/python/diffusers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/vall-e-x/ --grpc_python_out=backend/python/vall-e-x/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/vllm/ --grpc_python_out=backend/python/vllm/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/petals/ --grpc_python_out=backend/python/petals/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/exllama2/ --grpc_python_out=backend/python/exllama2/ backend/backend.proto
## GRPC
# Note: it is duplicated in the Dockerfile
feat(conda): conda environments (#1144) * feat(autogptq): add a separate conda environment for autogptq (#1137) **Description** This PR related to #1117 **Notes for Reviewers** Here we lock down the version of the dependencies. Make sure it can be used all the time without failed if the version of dependencies were upgraded. I change the order of importing packages according to the pylint, and no change the logic of code. It should be ok. I will do more investigate on writing some test cases for every backend. I can run the service in my environment, but there is not exist a way to test it. So, I am not confident on it. Add a README.md in the `grpc` root. This is the common commands for creating `conda` environment. And it can be used to the reference file for creating extral gRPC backend document. Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * [Extra backend] Add seperate environment for ttsbark (#1141) **Description** This PR relates to #1117 **Notes for Reviewers** Same to the latest PR: * The code is also changed, but only the order of the import package parts. And some code comments are also added. * Add a configuration of the `conda` environment * Add a simple test case for testing if the service can be startup in current `conda` environment. It is succeed in VSCode, but the it is not out of box on terminal. So, it is hard to say the test case really useful. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): add make target and entrypoints for the dockerfile Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add seperate conda env for diffusers (#1145) **Description** This PR relates to #1117 **Notes for Reviewers** * Add `conda` env `diffusers.yml` * Add Makefile to create it automatically * Add `run.sh` to support running as a extra backend * Also adding it to the main Dockerfile * Add make command in the root Makefile * Testing the server, it can start up under the env Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for vllm (#1148) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server can be started as normal * The test case can be triggered in VSCode * Same to other this kind of PRs, add `vllm.yml` Makefile and add `run.sh` to the main Dockerfile, and command to the main Makefile **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for huggingface (#1146) **Description** This PR is related to #1117 **Notes for Reviewers** * Add conda env `huggingface.yml` * Change the import order, and also remove the no-used packages * Add `run.sh` and `make command` to the main Dockerfile and Makefile * Add test cases for it. It can be triggered and succeed under VSCode Python extension but it is hang by using `python -m unites test_huggingface.py` in the terminal ``` Running tests (unittest): /workspaces/LocalAI/extra/grpc/huggingface Running tests: /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_embedding /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_load_model /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_server_startup ./test_huggingface.py::TestBackendServicer::test_embedding Passed ./test_huggingface.py::TestBackendServicer::test_load_model Passed ./test_huggingface.py::TestBackendServicer::test_server_startup Passed Total number of tests expected to run: 3 Total number of tests run: 3 Total number of tests passed: 3 Total number of tests failed: 0 Total number of tests failed with errors: 0 Total number of tests skipped: 0 Finished running tests! ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add the seperate conda env for VALL-E X (#1147) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server cannot start up ``` (ttsvalle) @Aisuko ➜ /workspaces/LocalAI (feat/vall-e-x) $ /opt/conda/envs/ttsvalle/bin/python /workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py Traceback (most recent call last): File "/workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py", line 14, in <module> from utils.generation import SAMPLE_RATE, generate_audio, preload_models ModuleNotFoundError: No module named 'utils' ``` The installation steps follow https://github.com/Plachtaa/VALL-E-X#-installation below: * Under the `ttsvalle` conda env ``` git clone https://github.com/Plachtaa/VALL-E-X.git cd VALL-E-X pip install -r requirements.txt ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: set image type Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate conda env for exllama (#1149) Add seperate env for exllama Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Setup conda Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set image_type arg Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: prepare only conda env in tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Dockerfile: comment manual pip calls Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * conda: add conda to PATH Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixes * add shebang * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * file perms Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * Install new conda in the worker * Disable GPU tests for now until the worker is back * Rename workflows * debug * Fixup conda install * fixup(wrapper): pass args Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Aisuko <urakiny@gmail.com>
2023-11-04 14:30:32 +00:00
prepare-extra-conda-environments:
$(MAKE) -C backend/python/autogptq
$(MAKE) -C backend/python/bark
$(MAKE) -C backend/python/diffusers
$(MAKE) -C backend/python/vllm
$(MAKE) -C backend/python/sentencetransformers
$(MAKE) -C backend/python/transformers
$(MAKE) -C backend/python/transformers-musicgen
$(MAKE) -C backend/python/vall-e-x
$(MAKE) -C backend/python/exllama
$(MAKE) -C backend/python/petals
$(MAKE) -C backend/python/exllama2
feat(conda): conda environments (#1144) * feat(autogptq): add a separate conda environment for autogptq (#1137) **Description** This PR related to #1117 **Notes for Reviewers** Here we lock down the version of the dependencies. Make sure it can be used all the time without failed if the version of dependencies were upgraded. I change the order of importing packages according to the pylint, and no change the logic of code. It should be ok. I will do more investigate on writing some test cases for every backend. I can run the service in my environment, but there is not exist a way to test it. So, I am not confident on it. Add a README.md in the `grpc` root. This is the common commands for creating `conda` environment. And it can be used to the reference file for creating extral gRPC backend document. Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * [Extra backend] Add seperate environment for ttsbark (#1141) **Description** This PR relates to #1117 **Notes for Reviewers** Same to the latest PR: * The code is also changed, but only the order of the import package parts. And some code comments are also added. * Add a configuration of the `conda` environment * Add a simple test case for testing if the service can be startup in current `conda` environment. It is succeed in VSCode, but the it is not out of box on terminal. So, it is hard to say the test case really useful. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): add make target and entrypoints for the dockerfile Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add seperate conda env for diffusers (#1145) **Description** This PR relates to #1117 **Notes for Reviewers** * Add `conda` env `diffusers.yml` * Add Makefile to create it automatically * Add `run.sh` to support running as a extra backend * Also adding it to the main Dockerfile * Add make command in the root Makefile * Testing the server, it can start up under the env Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for vllm (#1148) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server can be started as normal * The test case can be triggered in VSCode * Same to other this kind of PRs, add `vllm.yml` Makefile and add `run.sh` to the main Dockerfile, and command to the main Makefile **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for huggingface (#1146) **Description** This PR is related to #1117 **Notes for Reviewers** * Add conda env `huggingface.yml` * Change the import order, and also remove the no-used packages * Add `run.sh` and `make command` to the main Dockerfile and Makefile * Add test cases for it. It can be triggered and succeed under VSCode Python extension but it is hang by using `python -m unites test_huggingface.py` in the terminal ``` Running tests (unittest): /workspaces/LocalAI/extra/grpc/huggingface Running tests: /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_embedding /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_load_model /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_server_startup ./test_huggingface.py::TestBackendServicer::test_embedding Passed ./test_huggingface.py::TestBackendServicer::test_load_model Passed ./test_huggingface.py::TestBackendServicer::test_server_startup Passed Total number of tests expected to run: 3 Total number of tests run: 3 Total number of tests passed: 3 Total number of tests failed: 0 Total number of tests failed with errors: 0 Total number of tests skipped: 0 Finished running tests! ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add the seperate conda env for VALL-E X (#1147) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server cannot start up ``` (ttsvalle) @Aisuko ➜ /workspaces/LocalAI (feat/vall-e-x) $ /opt/conda/envs/ttsvalle/bin/python /workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py Traceback (most recent call last): File "/workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py", line 14, in <module> from utils.generation import SAMPLE_RATE, generate_audio, preload_models ModuleNotFoundError: No module named 'utils' ``` The installation steps follow https://github.com/Plachtaa/VALL-E-X#-installation below: * Under the `ttsvalle` conda env ``` git clone https://github.com/Plachtaa/VALL-E-X.git cd VALL-E-X pip install -r requirements.txt ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: set image type Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate conda env for exllama (#1149) Add seperate env for exllama Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Setup conda Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set image_type arg Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: prepare only conda env in tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Dockerfile: comment manual pip calls Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * conda: add conda to PATH Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixes * add shebang * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * file perms Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * Install new conda in the worker * Disable GPU tests for now until the worker is back * Rename workflows * debug * Fixup conda install * fixup(wrapper): pass args Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Aisuko <urakiny@gmail.com>
2023-11-04 14:30:32 +00:00
prepare-test-extra:
$(MAKE) -C backend/python/transformers
2023-12-11 07:20:34 +00:00
$(MAKE) -C backend/python/diffusers
test-extra: prepare-test-extra
$(MAKE) -C backend/python/transformers test
2023-12-11 07:20:34 +00:00
$(MAKE) -C backend/python/diffusers test
feat(conda): conda environments (#1144) * feat(autogptq): add a separate conda environment for autogptq (#1137) **Description** This PR related to #1117 **Notes for Reviewers** Here we lock down the version of the dependencies. Make sure it can be used all the time without failed if the version of dependencies were upgraded. I change the order of importing packages according to the pylint, and no change the logic of code. It should be ok. I will do more investigate on writing some test cases for every backend. I can run the service in my environment, but there is not exist a way to test it. So, I am not confident on it. Add a README.md in the `grpc` root. This is the common commands for creating `conda` environment. And it can be used to the reference file for creating extral gRPC backend document. Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * [Extra backend] Add seperate environment for ttsbark (#1141) **Description** This PR relates to #1117 **Notes for Reviewers** Same to the latest PR: * The code is also changed, but only the order of the import package parts. And some code comments are also added. * Add a configuration of the `conda` environment * Add a simple test case for testing if the service can be startup in current `conda` environment. It is succeed in VSCode, but the it is not out of box on terminal. So, it is hard to say the test case really useful. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): add make target and entrypoints for the dockerfile Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add seperate conda env for diffusers (#1145) **Description** This PR relates to #1117 **Notes for Reviewers** * Add `conda` env `diffusers.yml` * Add Makefile to create it automatically * Add `run.sh` to support running as a extra backend * Also adding it to the main Dockerfile * Add make command in the root Makefile * Testing the server, it can start up under the env Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for vllm (#1148) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server can be started as normal * The test case can be triggered in VSCode * Same to other this kind of PRs, add `vllm.yml` Makefile and add `run.sh` to the main Dockerfile, and command to the main Makefile **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate env for huggingface (#1146) **Description** This PR is related to #1117 **Notes for Reviewers** * Add conda env `huggingface.yml` * Change the import order, and also remove the no-used packages * Add `run.sh` and `make command` to the main Dockerfile and Makefile * Add test cases for it. It can be triggered and succeed under VSCode Python extension but it is hang by using `python -m unites test_huggingface.py` in the terminal ``` Running tests (unittest): /workspaces/LocalAI/extra/grpc/huggingface Running tests: /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_embedding /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_load_model /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_server_startup ./test_huggingface.py::TestBackendServicer::test_embedding Passed ./test_huggingface.py::TestBackendServicer::test_load_model Passed ./test_huggingface.py::TestBackendServicer::test_server_startup Passed Total number of tests expected to run: 3 Total number of tests run: 3 Total number of tests passed: 3 Total number of tests failed: 0 Total number of tests failed with errors: 0 Total number of tests skipped: 0 Finished running tests! ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda): Add the seperate conda env for VALL-E X (#1147) **Description** This PR is related to #1117 **Notes for Reviewers** * The gRPC server cannot start up ``` (ttsvalle) @Aisuko ➜ /workspaces/LocalAI (feat/vall-e-x) $ /opt/conda/envs/ttsvalle/bin/python /workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py Traceback (most recent call last): File "/workspaces/LocalAI/extra/grpc/vall-e-x/ttsvalle.py", line 14, in <module> from utils.generation import SAMPLE_RATE, generate_audio, preload_models ModuleNotFoundError: No module named 'utils' ``` The installation steps follow https://github.com/Plachtaa/VALL-E-X#-installation below: * Under the `ttsvalle` conda env ``` git clone https://github.com/Plachtaa/VALL-E-X.git cd VALL-E-X pip install -r requirements.txt ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions ------------------------- The draft above helps to give a quick overview of your PR. Remember to remove this comment and to at least: 1. Include descriptive PR titles with [<component-name>] prepended. We use [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). 2. Build and test your changes before submitting a PR (`make build`). 3. Sign your commits 4. **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below). 5. **X/Twitter handle:** we announce bigger features on X/Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. If no one reviews your PR within a few days, please @-mention @mudler. --> Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: set image type Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(conda):Add seperate conda env for exllama (#1149) Add seperate env for exllama Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Setup conda Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set image_type arg Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: prepare only conda env in tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Dockerfile: comment manual pip calls Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * conda: add conda to PATH Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixes * add shebang * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * file perms Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * Install new conda in the worker * Disable GPU tests for now until the worker is back * Rename workflows * debug * Fixup conda install * fixup(wrapper): pass args Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: GitHub <noreply@github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Aisuko <urakiny@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Aisuko <urakiny@gmail.com>
2023-11-04 14:30:32 +00:00
backend-assets/grpc:
mkdir -p backend-assets/grpc
backend-assets/grpc/llama: backend-assets/grpc sources/go-llama/libbinding.a
$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/sources/go-llama
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-llama LIBRARY_PATH=$(shell pwd)/sources/go-llama \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama ./backend/go/llm/llama/
# TODO: every binary should have its own folder instead, so can have different implementations
ifeq ($(BUILD_TYPE),metal)
cp backend/cpp/llama/llama.cpp/ggml-metal.metal backend-assets/grpc/
endif
## BACKEND CPP LLAMA START
# Sets the variables in case it has to build the gRPC locally.
INSTALLED_PACKAGES=$(CURDIR)/backend/cpp/grpc/installed_packages
INSTALLED_LIB_CMAKE=$(INSTALLED_PACKAGES)/lib/cmake
ADDED_CMAKE_ARGS=-Dabsl_DIR=${INSTALLED_LIB_CMAKE}/absl \
-DProtobuf_DIR=${INSTALLED_LIB_CMAKE}/protobuf \
-Dutf8_range_DIR=${INSTALLED_LIB_CMAKE}/utf8_range \
-DgRPC_DIR=${INSTALLED_LIB_CMAKE}/grpc \
-DCMAKE_CXX_STANDARD_INCLUDE_DIRECTORIES=${INSTALLED_PACKAGES}/include
backend/cpp/llama/grpc-server:
ifdef BUILD_GRPC_FOR_BACKEND_LLAMA
backend/cpp/grpc/script/build_grpc.sh ${INSTALLED_PACKAGES}
export _PROTOBUF_PROTOC=${INSTALLED_PACKAGES}/bin/proto && \
export _GRPC_CPP_PLUGIN_EXECUTABLE=${INSTALLED_PACKAGES}/bin/grpc_cpp_plugin && \
export PATH=${PATH}:${INSTALLED_PACKAGES}/bin && \
CMAKE_ARGS="${CMAKE_ARGS} ${ADDED_CMAKE_ARGS}" LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
else
echo "BUILD_GRPC_FOR_BACKEND_LLAMA is not defined."
LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
endif
## BACKEND CPP LLAMA END
##
backend-assets/grpc/llama-cpp: backend-assets/grpc backend/cpp/llama/grpc-server
cp -rfv backend/cpp/llama/grpc-server backend-assets/grpc/llama-cpp
# TODO: every binary should have its own folder instead, so can have different metal implementations
ifeq ($(BUILD_TYPE),metal)
cp backend/cpp/llama/llama.cpp/build/bin/ggml-metal.metal backend-assets/grpc/
endif
backend-assets/grpc/llama-ggml: backend-assets/grpc sources/go-llama-ggml/libbinding.a
$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/sources/go-llama-ggml
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-llama-ggml LIBRARY_PATH=$(shell pwd)/sources/go-llama-ggml \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama-ggml ./backend/go/llm/llama-ggml/
backend-assets/grpc/gpt4all: backend-assets/grpc backend-assets/gpt4all sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/gpt4all/gpt4all-bindings/golang/ LIBRARY_PATH=$(shell pwd)/sources/gpt4all/gpt4all-bindings/golang/ \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt4all ./backend/go/llm/gpt4all/
backend-assets/grpc/dolly: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/dolly ./backend/go/llm/dolly/
backend-assets/grpc/gpt2: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt2 ./backend/go/llm/gpt2/
backend-assets/grpc/gptj: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gptj ./backend/go/llm/gptj/
backend-assets/grpc/gptneox: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gptneox ./backend/go/llm/gptneox/
backend-assets/grpc/mpt: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/mpt ./backend/go/llm/mpt/
backend-assets/grpc/replit: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/replit ./backend/go/llm/replit/
backend-assets/grpc/falcon-ggml: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/falcon-ggml ./backend/go/llm/falcon-ggml/
backend-assets/grpc/starcoder: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/starcoder ./backend/go/llm/starcoder/
backend-assets/grpc/rwkv: backend-assets/grpc sources/go-rwkv/librwkv.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-rwkv LIBRARY_PATH=$(shell pwd)/sources/go-rwkv \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/rwkv ./backend/go/llm/rwkv
backend-assets/grpc/bert-embeddings: backend-assets/grpc sources/go-bert/libgobert.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-bert LIBRARY_PATH=$(shell pwd)/sources/go-bert \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/bert-embeddings ./backend/go/llm/bert/
backend-assets/grpc/langchain-huggingface: backend-assets/grpc
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/langchain-huggingface ./backend/go/llm/langchain/
backend-assets/grpc/stablediffusion: backend-assets/grpc
if [ ! -f backend-assets/grpc/stablediffusion ]; then \
$(MAKE) sources/go-stable-diffusion/libstablediffusion.a; \
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-stable-diffusion/ LIBRARY_PATH=$(shell pwd)/sources/go-stable-diffusion/ \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion ./backend/go/image/; \
fi
backend-assets/grpc/piper: backend-assets/grpc backend-assets/espeak-ng-data sources/go-piper/libpiper_binding.a
CGO_CXXFLAGS="$(PIPER_CGO_CXXFLAGS)" CGO_LDFLAGS="$(PIPER_CGO_LDFLAGS)" LIBRARY_PATH=$(shell pwd)/sources/go-piper \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/piper ./backend/go/tts/
backend-assets/grpc/whisper: backend-assets/grpc sources/whisper.cpp/libwhisper.a
CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/whisper.cpp LIBRARY_PATH=$(shell pwd)/sources/whisper.cpp \
$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/whisper ./backend/go/transcribe/
grpcs: prepare $(GRPC_BACKENDS)