LocalAI/extra/grpc/vllm/backend_vllm.py
Ettore Di Giacinto f347e51927
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 15:30:32 +01:00

163 lines
5.1 KiB
Python

#!/usr/bin/env python3
from concurrent import futures
import time
import argparse
import signal
import sys
import os
import backend_pb2
import backend_pb2_grpc
import grpc
from vllm import LLM, SamplingParams
_ONE_DAY_IN_SECONDS = 60 * 60 * 24
# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
# Implement the BackendServicer class with the service methods
class BackendServicer(backend_pb2_grpc.BackendServicer):
"""
A gRPC servicer that implements the Backend service defined in backend.proto.
"""
def generate(self,prompt, max_new_tokens):
"""
Generates text based on the given prompt and maximum number of new tokens.
Args:
prompt (str): The prompt to generate text from.
max_new_tokens (int): The maximum number of new tokens to generate.
Returns:
str: The generated text.
"""
self.generator.end_beam_search()
# Tokenizing the input
ids = self.generator.tokenizer.encode(prompt)
self.generator.gen_begin_reuse(ids)
initial_len = self.generator.sequence[0].shape[0]
has_leading_space = False
decoded_text = ''
for i in range(max_new_tokens):
token = self.generator.gen_single_token()
if i == 0 and self.generator.tokenizer.tokenizer.IdToPiece(int(token)).startswith(''):
has_leading_space = True
decoded_text = self.generator.tokenizer.decode(self.generator.sequence[0][initial_len:])
if has_leading_space:
decoded_text = ' ' + decoded_text
if token.item() == self.generator.tokenizer.eos_token_id:
break
return decoded_text
def Health(self, request, context):
"""
Returns a health check message.
Args:
request: The health check request.
context: The gRPC context.
Returns:
backend_pb2.Reply: The health check reply.
"""
return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
def LoadModel(self, request, context):
"""
Loads a language model.
Args:
request: The load model request.
context: The gRPC context.
Returns:
backend_pb2.Result: The load model result.
"""
try:
if request.Quantization != "":
self.llm = LLM(model=request.Model, quantization=request.Quantization)
else:
self.llm = LLM(model=request.Model)
except Exception as err:
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
return backend_pb2.Result(message="Model loaded successfully", success=True)
def Predict(self, request, context):
"""
Generates text based on the given prompt and sampling parameters.
Args:
request: The predict request.
context: The gRPC context.
Returns:
backend_pb2.Result: The predict result.
"""
if request.TopP == 0:
request.TopP = 0.9
sampling_params = SamplingParams(temperature=request.Temperature, top_p=request.TopP)
outputs = self.llm.generate([request.Prompt], sampling_params)
generated_text = outputs[0].outputs[0].text
# Remove prompt from response if present
if request.Prompt in generated_text:
generated_text = generated_text.replace(request.Prompt, "")
return backend_pb2.Result(message=bytes(generated_text, encoding='utf-8'))
def PredictStream(self, request, context):
"""
Generates text based on the given prompt and sampling parameters, and streams the results.
Args:
request: The predict stream request.
context: The gRPC context.
Returns:
backend_pb2.Result: The predict stream result.
"""
# Implement PredictStream RPC
#for reply in some_data_generator():
# yield reply
# Not implemented yet
return self.Predict(request, context)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()
print("Server started. Listening on: " + address, file=sys.stderr)
# Define the signal handler function
def signal_handler(sig, frame):
print("Received termination signal. Shutting down...")
server.stop(0)
sys.exit(0)
# Set the signal handlers for SIGINT and SIGTERM
signal.signal(signal.SIGINT, signal_handler)
signal.signal(signal.SIGTERM, signal_handler)
try:
while True:
time.sleep(_ONE_DAY_IN_SECONDS)
except KeyboardInterrupt:
server.stop(0)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Run the gRPC server.")
parser.add_argument(
"--addr", default="localhost:50051", help="The address to bind the server to."
)
args = parser.parse_args()
serve(args.addr)