LocalAI/Makefile

558 lines
20 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
GORELEASER?=
export BUILD_TYPE?=
GO_TAGS?=
BUILD_ID?=
NATIVE?=false
TEST_DIR=/tmp/test
TEST_FLAKES?=5
RANDOM := $(shell bash -c 'echo $$RANDOM')
VERSION?=$(shell git describe --always --tags || echo "dev" )
# go tool nm ./local-ai | grep Commit
LD_FLAGS?=-s -w
override LD_FLAGS += -X "github.com/mudler/LocalAI/internal.Version=$(VERSION)"
override LD_FLAGS += -X "github.com/mudler/LocalAI/internal.Commit=$(shell git rev-parse HEAD)"
OPTIONAL_TARGETS?=
export 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)
ifeq ($(OSX_SIGNING_IDENTITY),)
OSX_SIGNING_IDENTITY := $(shell security find-identity -v -p codesigning | grep '"' | head -n 1 | sed -E 's/.*"(.*)"/\1/')
endif
2023-05-24 14:42:24 +00:00
endif
# check if goreleaser exists
ifeq (, $(shell which goreleaser))
GORELEASER=curl -sfL https://goreleaser.com/static/run | bash -s --
else
GORELEASER=$(shell which goreleaser)
endif
TEST_PATHS?=./api/... ./pkg/... ./core/...
.PHONY: all test build vendor
all: help
## GENERIC
rebuild: ## Rebuilds the project
2023-07-05 16:24:55 +00:00
$(GOCMD) clean -cache
$(MAKE) build
clean: ## Remove build related file
2023-07-05 16:24:55 +00:00
$(GOCMD) clean -cache
rm -f prepare
rm -rf $(BINARY_NAME)
rm -rf release/
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
$(MAKE) protogen-clean
rmdir pkg/grpc/proto || true
clean-tests:
rm -rf test-models
rm -rf test-dir
## Install Go tools
install-go-tools:
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
## Build:
build: protogen-go install-go-tools ## 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})
$(info ${GREEN}I UPX: ${YELLOW}$(UPX)${RESET})
rm -rf $(BINARY_NAME) || true
CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./
dev-dist:
$(GORELEASER) build --snapshot --clean
feat: auto select llama-cpp cuda runtime (#2306) * auto select cpu variant Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * remove cuda target for now Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * fix metal Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * fix path Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * cuda Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * auto select cuda Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * update test Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * select CUDA backend only if present Signed-off-by: mudler <mudler@localai.io> * ci: keep cuda bin in path Signed-off-by: mudler <mudler@localai.io> * Makefile: make dist now builds also cuda Signed-off-by: mudler <mudler@localai.io> * Keep pushing fallback in case auto-flagset/nvidia fails There could be other reasons for which the default binary may fail. For example we might have detected an Nvidia GPU, however the user might not have the drivers/cuda libraries installed in the system, and so it would fail to start. We keep the fallback of llama.cpp at the end of the llama.cpp backends to try to fallback loading in case things go wrong Signed-off-by: mudler <mudler@localai.io> * Do not build cuda on MacOS Signed-off-by: mudler <mudler@localai.io> * cleanup Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * Apply suggestions from code review Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> --------- Signed-off-by: Sertac Ozercan <sozercan@gmail.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Signed-off-by: mudler <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: mudler <mudler@localai.io>
2024-05-14 17:40:18 +00:00
dist:
$(GORELEASER) build --clean
osx-signed: build
codesign --deep --force --sign "$(OSX_SIGNING_IDENTITY)" --entitlements "./Entitlements.plist" "./$(BINARY_NAME)"
## Run
run: ## run local-ai
CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) run ./
test-models/testmodel.ggml:
mkdir test-models
mkdir test-dir
wget -q https://huggingface.co/mradermacher/gpt2-alpaca-gpt4-GGUF/resolve/main/gpt2-alpaca-gpt4.Q4_K_M.gguf -O test-models/testmodel.ggml
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/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
cp tests/models_fixtures/* test-models
prepare-test: protogen-go
cp tests/models_fixtures/* test-models
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
########################################################
## Tests
########################################################
## Test targets
test: test-models/testmodel.ggml protogen-go
@echo 'Running tests'
export GO_TAGS="debug"
$(MAKE) prepare-test
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
HUGGINGFACE_GRPC=$(abspath ./)/backend/python/transformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!llama-gguf" --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
$(MAKE) test-llama-gguf
$(MAKE) test-tts
$(MAKE) test-stablediffusion
backends/llama-cpp: docker-build-llama-cpp docker-save-llama-cpp build
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
./local-ai backends install "ocifile://$(abspath ./backend-images/llama-cpp.tar)"
backends/piper: docker-build-piper docker-save-piper build
./local-ai backends install "ocifile://$(abspath ./backend-images/piper.tar)"
backends/stablediffusion-ggml: docker-build-stablediffusion-ggml docker-save-stablediffusion-ggml build
./local-ai backends install "ocifile://$(abspath ./backend-images/stablediffusion-ggml.tar)"
backends/whisper: docker-build-whisper docker-save-whisper build
./local-ai backends install "ocifile://$(abspath ./backend-images/whisper.tar)"
backends/silero-vad: docker-build-silero-vad docker-save-silero-vad build
./local-ai backends install "ocifile://$(abspath ./backend-images/silero-vad.tar)"
backends/local-store: docker-build-local-store docker-save-local-store build
./local-ai backends install "ocifile://$(abspath ./backend-images/local-store.tar)"
backends/huggingface: docker-build-huggingface docker-save-huggingface build
./local-ai backends install "ocifile://$(abspath ./backend-images/huggingface.tar)"
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
########################################################
## AIO tests
########################################################
docker-build-aio:
docker build --build-arg MAKEFLAGS="--jobs=5 --output-sync=target" -t local-ai:tests -f Dockerfile .
BASE_IMAGE=local-ai:tests DOCKER_AIO_IMAGE=local-ai-aio:test $(MAKE) docker-aio
e2e-aio:
LOCALAI_BACKEND_DIR=$(abspath ./backends) \
LOCALAI_MODELS_DIR=$(abspath ./models) \
LOCALAI_IMAGE_TAG=test \
LOCALAI_IMAGE=local-ai-aio \
$(MAKE) run-e2e-aio
run-e2e-aio: protogen-go
@echo 'Running e2e AIO tests'
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) -v -r ./tests/e2e-aio
########################################################
## E2E tests
########################################################
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 IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=0 -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 $(TEST_FLAKES) -v -r ./tests/e2e
teardown-e2e:
rm -rf $(TEST_DIR) || true
docker stop $$(docker ps -q --filter ancestor=localai-tests)
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
########################################################
## Integration and unit tests
########################################################
test-llama-gguf: prepare-test
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama-gguf" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
test-tts: prepare-test
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="tts" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
test-stablediffusion: prepare-test
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="stablediffusion" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
test-stores:
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="stores" --flake-attempts $(TEST_FLAKES) -v -r tests/integration
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
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
########################################################
## Help
########################################################
## 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)
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
########################################################
## Backends
########################################################
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: protogen
protogen: protogen-go protogen-python
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: protogen-clean
protogen-clean: protogen-go-clean protogen-python-clean
protoc:
@OS_NAME=$$(uname -s | tr '[:upper:]' '[:lower:]'); \
ARCH_NAME=$$(uname -m); \
if [ "$$OS_NAME" = "darwin" ]; then \
if [ "$$ARCH_NAME" = "arm64" ]; then \
FILE=protoc-31.1-osx-aarch_64.zip; \
elif [ "$$ARCH_NAME" = "x86_64" ]; then \
FILE=protoc-31.1-osx-x86_64.zip; \
else \
echo "Unsupported macOS architecture: $$ARCH_NAME"; exit 1; \
fi; \
elif [ "$$OS_NAME" = "linux" ]; then \
if [ "$$ARCH_NAME" = "x86_64" ]; then \
FILE=protoc-31.1-linux-x86_64.zip; \
elif [ "$$ARCH_NAME" = "aarch64" ] || [ "$$ARCH_NAME" = "arm64" ]; then \
FILE=protoc-31.1-linux-aarch_64.zip; \
elif [ "$$ARCH_NAME" = "ppc64le" ]; then \
FILE=protoc-31.1-linux-ppcle_64.zip; \
elif [ "$$ARCH_NAME" = "s390x" ]; then \
FILE=protoc-31.1-linux-s390_64.zip; \
elif [ "$$ARCH_NAME" = "i386" ] || [ "$$ARCH_NAME" = "x86" ]; then \
FILE=protoc-31.1-linux-x86_32.zip; \
else \
echo "Unsupported Linux architecture: $$ARCH_NAME"; exit 1; \
fi; \
else \
echo "Unsupported OS: $$OS_NAME"; exit 1; \
fi; \
URL=https://github.com/protocolbuffers/protobuf/releases/download/v31.1/$$FILE; \
curl -L -s $$URL -o protoc.zip && \
unzip -j -d $(CURDIR) protoc.zip bin/protoc && rm protoc.zip
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: protogen-go
protogen-go: protoc install-go-tools
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
mkdir -p pkg/grpc/proto
./protoc --experimental_allow_proto3_optional -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
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: protogen-go-clean
protogen-go-clean:
$(RM) pkg/grpc/proto/backend.pb.go pkg/grpc/proto/backend_grpc.pb.go
$(RM) bin/*
.PHONY: protogen-python
protogen-python: bark-protogen coqui-protogen chatterbox-protogen diffusers-protogen exllama2-protogen rerankers-protogen transformers-protogen kokoro-protogen vllm-protogen faster-whisper-protogen
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: protogen-python-clean
protogen-python-clean: bark-protogen-clean coqui-protogen-clean chatterbox-protogen-clean diffusers-protogen-clean exllama2-protogen-clean rerankers-protogen-clean transformers-protogen-clean kokoro-protogen-clean vllm-protogen-clean faster-whisper-protogen-clean
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: bark-protogen
bark-protogen:
$(MAKE) -C backend/python/bark protogen
.PHONY: bark-protogen-clean
bark-protogen-clean:
$(MAKE) -C backend/python/bark protogen-clean
.PHONY: coqui-protogen
coqui-protogen:
$(MAKE) -C backend/python/coqui protogen
.PHONY: coqui-protogen-clean
coqui-protogen-clean:
$(MAKE) -C backend/python/coqui protogen-clean
.PHONY: diffusers-protogen
diffusers-protogen:
$(MAKE) -C backend/python/diffusers protogen
.PHONY: chatterbox-protogen
chatterbox-protogen:
$(MAKE) -C backend/python/chatterbox protogen
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: diffusers-protogen-clean
diffusers-protogen-clean:
$(MAKE) -C backend/python/diffusers protogen-clean
.PHONY: chatterbox-protogen-clean
chatterbox-protogen-clean:
$(MAKE) -C backend/python/chatterbox protogen-clean
.PHONY: faster-whisper-protogen
faster-whisper-protogen:
$(MAKE) -C backend/python/faster-whisper protogen
.PHONY: faster-whisper-protogen-clean
faster-whisper-protogen-clean:
$(MAKE) -C backend/python/faster-whisper protogen-clean
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: exllama2-protogen
exllama2-protogen:
$(MAKE) -C backend/python/exllama2 protogen
.PHONY: exllama2-protogen-clean
exllama2-protogen-clean:
$(MAKE) -C backend/python/exllama2 protogen-clean
.PHONY: rerankers-protogen
rerankers-protogen:
$(MAKE) -C backend/python/rerankers protogen
.PHONY: rerankers-protogen-clean
rerankers-protogen-clean:
$(MAKE) -C backend/python/rerankers protogen-clean
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: transformers-protogen
transformers-protogen:
$(MAKE) -C backend/python/transformers protogen
.PHONY: transformers-protogen-clean
transformers-protogen-clean:
$(MAKE) -C backend/python/transformers protogen-clean
.PHONY: kokoro-protogen
kokoro-protogen:
$(MAKE) -C backend/python/kokoro protogen
.PHONY: kokoro-protogen-clean
kokoro-protogen-clean:
$(MAKE) -C backend/python/kokoro protogen-clean
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
.PHONY: vllm-protogen
vllm-protogen:
$(MAKE) -C backend/python/vllm protogen
.PHONY: vllm-protogen-clean
vllm-protogen-clean:
$(MAKE) -C backend/python/vllm protogen-clean
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
fix: dont commit generated files to git (#1993) * fix: initial work towards not committing generated files to the repository Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * feat: improve build docs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove unused folder from .dockerignore and .gitignore Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix extra backend tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: attempt to fix other tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more test fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: fix apple tests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more extras tests fixes Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add GOBIN to PATH in docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: extra tests and Dockerfile corrections Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove build dependency checks Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add golang protobuf compilers to tests-linux action Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: ensure protogen is run for extra backend installs Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: use newer protobuf Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: more missing protoc binaries Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: missing dependencies during docker build Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: don't install grpc compilers in the final stage if they aren't needed Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: python-grpc-tools in 22.04 repos is too old Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: add a couple of extra build dependencies to Makefile Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: unbreak container rebuild functionality Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-13 07:37:32 +00:00
prepare-test-extra: protogen-python
$(MAKE) -C backend/python/transformers
2023-12-11 07:20:34 +00:00
$(MAKE) -C backend/python/diffusers
$(MAKE) -C backend/python/chatterbox
$(MAKE) -C backend/python/vllm
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
$(MAKE) -C backend/python/chatterbox test
$(MAKE) -C backend/python/vllm 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
DOCKER_IMAGE?=local-ai
DOCKER_AIO_IMAGE?=local-ai-aio
IMAGE_TYPE?=core
BASE_IMAGE?=ubuntu:22.04
docker:
docker build \
--build-arg BASE_IMAGE=$(BASE_IMAGE) \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="$(GO_TAGS)" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
--build-arg BUILD_TYPE=$(BUILD_TYPE) \
-t $(DOCKER_IMAGE) .
docker-cuda11:
docker build \
--build-arg CUDA_MAJOR_VERSION=11 \
--build-arg CUDA_MINOR_VERSION=8 \
--build-arg BASE_IMAGE=$(BASE_IMAGE) \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="$(GO_TAGS)" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
--build-arg BUILD_TYPE=$(BUILD_TYPE) \
-t $(DOCKER_IMAGE)-cuda11 .
docker-aio:
@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"
docker build \
--build-arg BASE_IMAGE=$(BASE_IMAGE) \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
-t $(DOCKER_AIO_IMAGE) -f Dockerfile.aio .
docker-aio-all:
$(MAKE) docker-aio DOCKER_AIO_SIZE=cpu
$(MAKE) docker-aio DOCKER_AIO_SIZE=cpu
docker-image-intel:
docker build \
--build-arg BASE_IMAGE=intel/oneapi-basekit:${ONEAPI_VERSION}.0-0-devel-ubuntu24.04 \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="$(GO_TAGS)" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
--build-arg BUILD_TYPE=sycl_f32 -t $(DOCKER_IMAGE) .
docker-image-intel-xpu:
docker build \
--build-arg BASE_IMAGE=intel/oneapi-basekit:${ONEAPI_VERSION}.0-0-devel-ubuntu22.04 \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="$(GO_TAGS)" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
--build-arg BUILD_TYPE=sycl_f32 -t $(DOCKER_IMAGE) .
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
########################################################
## Backends
########################################################
backend-images:
mkdir -p backend-images
docker-build-llama-cpp:
docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg IMAGE_BASE=$(IMAGE_BASE) -t local-ai-backend:llama-cpp -f backend/Dockerfile.llama-cpp .
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
docker-build-bark-cpp:
docker build -t local-ai-backend:bark-cpp -f backend/Dockerfile.go --build-arg BACKEND=bark-cpp .
docker-build-piper:
docker build -t local-ai-backend:piper -f backend/Dockerfile.go --build-arg BACKEND=piper .
docker-build-local-store:
docker build -t local-ai-backend:local-store -f backend/Dockerfile.go --build-arg BACKEND=local-store .
docker-build-huggingface:
docker build -t local-ai-backend:huggingface -f backend/Dockerfile.go --build-arg BACKEND=huggingface .
docker-save-huggingface: backend-images
docker save local-ai-backend:huggingface -o backend-images/huggingface.tar
docker-save-local-store: backend-images
docker save local-ai-backend:local-store -o backend-images/local-store.tar
docker-build-silero-vad:
docker build -t local-ai-backend:silero-vad -f backend/Dockerfile.go --build-arg BACKEND=silero-vad .
docker-save-silero-vad: backend-images
docker save local-ai-backend:silero-vad -o backend-images/silero-vad.tar
docker-save-piper: backend-images
docker save local-ai-backend:piper -o backend-images/piper.tar
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
docker-save-llama-cpp: backend-images
docker save local-ai-backend:llama-cpp -o backend-images/llama-cpp.tar
docker-save-bark-cpp: backend-images
docker save local-ai-backend:bark-cpp -o backend-images/bark-cpp.tar
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
docker-build-stablediffusion-ggml:
docker build -t local-ai-backend:stablediffusion-ggml -f backend/Dockerfile.go --build-arg BACKEND=stablediffusion-ggml .
docker-save-stablediffusion-ggml: backend-images
docker save local-ai-backend:stablediffusion-ggml -o backend-images/stablediffusion-ggml.tar
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
docker-build-rerankers:
docker build -t local-ai-backend:rerankers -f backend/Dockerfile.python --build-arg BACKEND=rerankers .
docker-build-vllm:
docker build -t local-ai-backend:vllm -f backend/Dockerfile.python --build-arg BACKEND=vllm .
docker-build-transformers:
docker build -t local-ai-backend:transformers -f backend/Dockerfile.python --build-arg BACKEND=transformers .
docker-build-diffusers:
docker build -t local-ai-backend:diffusers -f backend/Dockerfile.python --build-arg BACKEND=diffusers .
docker-build-kokoro:
docker build -t local-ai-backend:kokoro -f backend/Dockerfile.python --build-arg BACKEND=kokoro .
docker-build-whisper:
docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:whisper -f backend/Dockerfile.go --build-arg BACKEND=whisper .
docker-save-whisper: backend-images
docker save local-ai-backend:whisper -o backend-images/whisper.tar
feat: do not bundle llama-cpp anymore (#5790) * Build llama.cpp separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Start to try to attach some tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add git and small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correctly autoload external backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run AIO tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly update the Makefile helps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt auto-bumper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run linux test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add llama-cpp into build pipelines Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add default capability (for cpu) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop llama-cpp specific logic from the backend loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop grpc install in ci for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pass by backends path for tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build protogen at start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(tests): set backends path consistently Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly configure the backends path Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to build for darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Compile for metal on arm64/darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to run build off from cross-arch Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to the backend index nvidia-l4t and cpu's llama-cpp backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Build also darwin-x86 for llama-cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Disable arm64 builds temporary Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test backend build on PR Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup build backend reusable workflow Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pass by skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use crane Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Skip drivers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * x86 darwin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add packaging step for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix leftover from bark-cpp extraction Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix hipblas build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 11:24:12 +00:00
docker-build-faster-whisper:
docker build -t local-ai-backend:faster-whisper -f backend/Dockerfile.python --build-arg BACKEND=faster-whisper .
docker-build-coqui:
docker build -t local-ai-backend:coqui -f backend/Dockerfile.python --build-arg BACKEND=coqui .
docker-build-bark:
docker build -t local-ai-backend:bark -f backend/Dockerfile.python --build-arg BACKEND=bark .
docker-build-chatterbox:
docker build -t local-ai-backend:chatterbox -f backend/Dockerfile.python --build-arg BACKEND=chatterbox .
docker-build-exllama2:
docker build -t local-ai-backend:exllama2 -f backend/Dockerfile.python --build-arg BACKEND=exllama2 .
docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-bark docker-build-chatterbox docker-build-exllama2
########################################################
### END Backends
########################################################
.PHONY: swagger
swagger:
swag init -g core/http/app.go --output swagger
.PHONY: gen-assets
gen-assets:
$(GOCMD) run core/dependencies_manager/manager.go webui_static.yaml core/http/static/assets
## Documentation
docs/layouts/_default:
mkdir -p docs/layouts/_default
docs/static/gallery.html: docs/layouts/_default
$(GOCMD) run ./.github/ci/modelslist.go ./gallery/index.yaml > docs/static/gallery.html
docs/public: docs/layouts/_default docs/static/gallery.html
cd docs && hugo --minify
docs-clean:
rm -rf docs/public
rm -rf docs/static/gallery.html
.PHONY: docs
docs: docs/static/gallery.html
cd docs && hugo serve