* feat(llama.cpp): Enable decentralized, distributed inference
As https://github.com/mudler/LocalAI/pull/2324 introduced distributed inferencing thanks to
@rgerganov implementation in https://github.com/ggerganov/llama.cpp/pull/6829 in upstream llama.cpp, now
it is possible to distribute the workload to remote llama.cpp gRPC server.
This changeset now uses mudler/edgevpn to establish a secure, distributed network between the nodes using a shared token.
The token is generated automatically when starting the server with the `--p2p` flag, and can be used by starting the workers
with `local-ai worker p2p-llama-cpp-rpc` by passing the token via environment variable (TOKEN) or with args (--token).
As per how mudler/edgevpn works, a network is established between the server and the workers with dht and mdns discovery protocols,
the llama.cpp rpc server is automatically started and exposed to the underlying p2p network so the API server can connect on.
When the HTTP server is started, it will discover the workers in the network and automatically create the port-forwards to the service locally.
Then llama.cpp is configured to use the services.
This feature is behind the "p2p" GO_FLAGS
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* go mod tidy
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: add p2p tag
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* better message
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parler-tts): Add new backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parler-tts): try downgrade protobuf
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parler-tts): add parler conda env
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Revert "feat(parler-tts): try downgrade protobuf"
This reverts commit bd5941d5cfc00676b45a99f71debf3c34249cf3c.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* deps: add grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: try to gen proto with same environment
* workaround
* Revert "fix: try to gen proto with same environment"
This reverts commit 998c745e2f.
* Workaround fixup
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
* feat(build): adjust number of parallel make jobs
* fix: update make on MacOS from brew to support --output-sync argument
* fix: cache grpc with version as part of key to improve validity of cache hits
* fix: use gmake for tests-apple to use the updated GNU make version
* fix: actually use the new make version for tests-apple
* feat: parallelize tests-extra
* feat: attempt to cache grpc build for docker images
* fix: don't quote GRPC version
* fix: don't cache go modules, we have limited cache space, better used elsewhere
* fix: release with the same version of go that we test with
* fix: don't fail on exporting cache layers
* fix: remove deprecated BUILD_GRPC docker arg from Makefile
* docs(aio): Add AIO images docs
* add image generation link to quickstart
* while reviewing I noticed this one link was missing, so quickly adding it.
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
* test with gguf instead of ggml. Updates testPrompt to match? Adds debugging line to Dockerfile that I've found helpful recently.
* fix testPrompt slightly
* Sad Experiment: Test GH runner without metal?
* break apart CGO_LDFLAGS
* switch runner
* upstream llama.cpp disables Metal on Github CI!
* missed a dir from clean-tests
* CGO_LDFLAGS
* tmate failure + NO_ACCELERATE
* whisper.cpp has a metal fix
* do the exact opposite of the name of this branch, but keep it around for unrelated fixes?
* add back newlines
* add tmate to linux for testing
* update fixtures
* timeout for tmate
* fix: clean up Makefile dependencies to allow for parallel builds
* refactor: remove old unused backend from Makefile
* fix: finish removing legacy backend, update piper
* fix: I broke llama... I fixed llama
* feat: give the tests and builds a few threads
* fix: ensure libraries are replaced before build, add dropreplace target
* Fix image build workflows
* feat(intel): add diffusers support
* try to consume upstream container image
* Debug
* Manually install deps
* Map transformers/hf cache dir to modelpath if not specified
* fix(compel): update initialization, pass by all gRPC options
* fix: add dependencies, implement transformers for xpu
* base it from the oneapi image
* Add pillow
* set threads if specified when launching the API
* Skip conda install if intel
* defaults to non-intel
* ci: add to pipelines
* prepare compel only if enabled
* Skip conda install if intel
* fix cleanup
* Disable compel by default
* Install torch 2.1.0 with Intel
* Skip conda on some setups
* Detect python
* Quiet output
* Do not override system python with conda
* Prefer python3
* Fixups
* exllama2: do not install without conda (overrides pytorch version)
* exllama/exllama2: do not install if not using cuda
* Add missing dataset dependency
* Small fixups, symlink to python, add requirements
* Add neural_speed to the deps
* correctly handle model offloading
* fix: device_map == xpu
* go back at calling python, fixed at dockerfile level
* Exllama2 restricted to only nvidia gpus
* Tokenizer to xpu
* Dockerfile changes to build for ROCm
* Adjust linker flags for ROCm
* Update conda env for diffusers and transformers to use ROCm pytorch
* Update transformers conda env for ROCm
* ci: build hipblas images
* fixup rebase
* use self-hosted
Signed-off-by: mudler <mudler@localai.io>
* specify LD_LIBRARY_PATH only when BUILD_TYPE=hipblas
---------
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: mudler <mudler@localai.io>
* feat(refactor): refactor config and input reading
* feat(tts): read config file for TTS
* examples(kubernetes): Add simple deployment example
* examples(kubernetes): Add simple deployment for intel arc
* docs(sycl): add sycl example
* feat(tts): do not always pick a first model
* fixups to run vall-e-x on container
* Correctly resolve backend
* cleanup backends
* switch image to ubuntu 22.04
* adapt commands for ubuntu
* transformers cleanup
* no contrib on ubuntu
* Change test model to gguf
* ci: disable bark tests (too cpu-intensive)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* cleanup
* refinements
* use intel base image
* Makefile: Add docker targets
* Change test model
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update huggingface.py
Switch SentenceTransformer for AutoModel in order to set trust_remote_code needed to use the encode method with embeddings models like jinai-v2
Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
* feat(transformers): split in separate backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
* refactor: rename llama-stable to llama-ggml
* Makefile: get sources in sources/
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixup path
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixup sources
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups sd
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* update SD
* fixup
* fixup: create piper libdir also when not built
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix make target on linux test
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor: move backends into the backends directory
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor: move main close to implementation for every backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* 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>
This change facilitates users working behind corporate firewalls or proxies. By allowing the integration of custom CA certificates, users can handle SSL connections that are intercepted by company infrastructure.
* wip: llama.cpp c++ gRPC server
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* make it work, attach it to the build process
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* update deps
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: add protobuf dep
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* try fix protobuf on cmake
* cmake: workarounds
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* add packages
* cmake: use fixed version of grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* cmake(grpc): install locally
* install grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* install required deps for grpc on debian bullseye
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* debug
* debug
* Fixups
* no need to install cmake manually
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: fixup macOS
* use brew whenever possible
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* macOS fixups
* debug
* fix container build
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* workaround
* try mac
https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def
* Disable temp. arm64 docker image builds
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
