mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 10:35:01 +00:00
chore: drop petals (#3316)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
GitHub
parent
1d651bbfad
commit
9475a6fa05
18 changed files with 3 additions and 319 deletions
|
|
@ -1,31 +0,0 @@
|
|||
.PHONY: petals
|
||||
petals: protogen
|
||||
@echo "Creating virtual environment..."
|
||||
bash install.sh "petals.yml"
|
||||
@echo "Virtual environment created."
|
||||
|
||||
.PHONY: run
|
||||
run: protogen
|
||||
@echo "Running petals..."
|
||||
bash run.sh
|
||||
@echo "petals run."
|
||||
|
||||
.PHONY: test
|
||||
test: protogen
|
||||
@echo "Testing petals..."
|
||||
bash test.sh
|
||||
@echo "petals tested."
|
||||
|
||||
.PHONY: protogen
|
||||
protogen: backend_pb2_grpc.py backend_pb2.py
|
||||
|
||||
.PHONY: protogen-clean
|
||||
protogen-clean:
|
||||
$(RM) backend_pb2_grpc.py backend_pb2.py
|
||||
|
||||
backend_pb2_grpc.py backend_pb2.py:
|
||||
python3 -m grpc_tools.protoc -I../.. --python_out=. --grpc_python_out=. backend.proto
|
||||
|
||||
.PHONY: clean
|
||||
clean: protogen-clean
|
||||
rm -rf venv __pycache__
|
||||
|
|
@ -1,140 +0,0 @@
|
|||
#!/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
|
||||
import torch
|
||||
from transformers import AutoTokenizer
|
||||
from petals import AutoDistributedModelForCausalLM
|
||||
|
||||
_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 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:
|
||||
self.tokenizer = AutoTokenizer.from_pretrained(request.Model, use_fast=False, add_bos_token=False)
|
||||
self.model = AutoDistributedModelForCausalLM.from_pretrained(request.Model)
|
||||
self.cuda = False
|
||||
if request.CUDA:
|
||||
self.model = self.model.cuda()
|
||||
self.cuda = True
|
||||
|
||||
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.
|
||||
"""
|
||||
|
||||
inputs = self.tokenizer(request.Prompt, return_tensors="pt")["input_ids"]
|
||||
if self.cuda:
|
||||
inputs = inputs.cuda()
|
||||
|
||||
if request.Tokens == 0:
|
||||
# Max to max value if tokens are not specified
|
||||
request.Tokens = 8192
|
||||
|
||||
# TODO: kwargs and map all parameters
|
||||
outputs = self.model.generate(inputs, max_new_tokens=request.Tokens)
|
||||
|
||||
generated_text = self.tokenizer.decode(outputs[0])
|
||||
# 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)
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
source $(dirname $0)/../common/libbackend.sh
|
||||
|
||||
# This is here because the Intel pip index is broken and returns 200 status codes for every package name, it just doesn't return any package links.
|
||||
# This makes uv think that the package exists in the Intel pip index, and by default it stops looking at other pip indexes once it finds a match.
|
||||
# We need uv to continue falling through to the pypi default index to find optimum[openvino] in the pypi index
|
||||
# the --upgrade actually allows us to *downgrade* torch to the version provided in the Intel pip index
|
||||
if [ "x${BUILD_PROFILE}" == "xintel" ]; then
|
||||
EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
|
||||
fi
|
||||
|
||||
installRequirements
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
transformers
|
||||
accelerate
|
||||
torch
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
--extra-index-url https://download.pytorch.org/whl/cu118
|
||||
torch
|
||||
transformers
|
||||
|
|
@ -1,2 +0,0 @@
|
|||
torch
|
||||
transformers
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
--extra-index-url https://download.pytorch.org/whl/rocm6.0
|
||||
torch
|
||||
transformers
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
--extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
intel-extension-for-pytorch
|
||||
torch
|
||||
optimum[openvino]
|
||||
setuptools==72.1.0 # https://github.com/mudler/LocalAI/issues/2406
|
||||
transformers
|
||||
|
|
@ -1,2 +0,0 @@
|
|||
git+https://github.com/bigscience-workshop/petals
|
||||
certifi
|
||||
|
|
@ -1,4 +0,0 @@
|
|||
#!/bin/bash
|
||||
source $(dirname $0)/../common/libbackend.sh
|
||||
|
||||
startBackend $@
|
||||
|
|
@ -1,58 +0,0 @@
|
|||
import unittest
|
||||
import subprocess
|
||||
import time
|
||||
import backend_pb2
|
||||
import backend_pb2_grpc
|
||||
|
||||
import grpc
|
||||
|
||||
import unittest
|
||||
import subprocess
|
||||
import time
|
||||
import grpc
|
||||
import backend_pb2_grpc
|
||||
import backend_pb2
|
||||
|
||||
class TestBackendServicer(unittest.TestCase):
|
||||
"""
|
||||
TestBackendServicer is the class that tests the gRPC service.
|
||||
|
||||
This class contains methods to test the startup and shutdown of the gRPC service.
|
||||
"""
|
||||
def setUp(self):
|
||||
self.service = subprocess.Popen(["python", "backend.py", "--addr", "localhost:50051"])
|
||||
time.sleep(10)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self.service.terminate()
|
||||
self.service.wait()
|
||||
|
||||
def test_server_startup(self):
|
||||
try:
|
||||
self.setUp()
|
||||
with grpc.insecure_channel("localhost:50051") as channel:
|
||||
stub = backend_pb2_grpc.BackendStub(channel)
|
||||
response = stub.Health(backend_pb2.HealthMessage())
|
||||
self.assertEqual(response.message, b'OK')
|
||||
except Exception as err:
|
||||
print(err)
|
||||
self.fail("Server failed to start")
|
||||
finally:
|
||||
self.tearDown()
|
||||
def test_load_model(self):
|
||||
"""
|
||||
This method tests if the model is loaded successfully
|
||||
"""
|
||||
try:
|
||||
self.setUp()
|
||||
with grpc.insecure_channel("localhost:50051") as channel:
|
||||
stub = backend_pb2_grpc.BackendStub(channel)
|
||||
response = stub.LoadModel(backend_pb2.ModelOptions(Model="bigscience/bloom-560m"))
|
||||
print(response)
|
||||
self.assertTrue(response.success)
|
||||
self.assertEqual(response.message, "Model loaded successfully")
|
||||
except Exception as err:
|
||||
print(err)
|
||||
self.fail("LoadModel service failed")
|
||||
finally:
|
||||
self.tearDown()
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
source $(dirname $0)/../common/libbackend.sh
|
||||
|
||||
runUnittests
|
||||
Loading…
Add table
Add a link
Reference in a new issue