share diffusers and petals

This commit is contained in:
Ettore Di Giacinto 2023-12-20 00:04:57 +00:00
parent b6256bf2e4
commit 244bf470ee
9 changed files with 179 additions and 14 deletions

View file

@ -1,11 +1,15 @@
.PHONY: petals
petals:
@echo "Creating virtual environment..."
@conda env create --name petals --file petals.yml
@echo "Virtual environment created."
$(MAKE) -C ../common-env/transformers
.PHONY: run
run:
@echo "Running petals..."
bash run.sh
@echo "petals run."
.PHONY: test
test:
@echo "Testing petals..."
bash test.sh
@echo "petals tested."

View file

@ -9,10 +9,10 @@ export PATH=$PATH:/opt/conda/bin
# if source is available use it, or use conda
#
if [ -f /opt/conda/bin/activate ]; then
source activate petals
source activate transformers
else
eval "$(conda shell.bash hook)"
conda activate petals
conda activate transformers
fi
# get the directory where the bash script is located

View file

@ -0,0 +1,11 @@
#!/bin/bash
##
## A bash script wrapper that runs the transformers server with conda
# Activate conda environment
source activate transformers
# get the directory where the bash script is located
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
python -m unittest $DIR/test_petals.py

View file

@ -0,0 +1,76 @@
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_petals.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="petals-team/StableBeluga"))
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()
def test_text(self):
"""
This method tests if the embeddings are generated 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="petals-team/StableBeluga"))
self.assertTrue(response.success)
req = backend_pb2.PredictOptions(prompt="The capital of France is")
resp = stub.Predict(req)
self.assertIsNotNone(resp.message)
except Exception as err:
print(err)
self.fail("text service failed")
finally:
self.tearDown()