mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-21 02:55:01 +00:00
feat(conda): share envs with transformer-based backends (#1465)
* feat(conda): share env between diffusers and bark
* Detect if env already exists
* share diffusers and petals
* tests: add petals
* Use smaller model for tests with petals
* test only model load on petals
* tests(petals): run only load model tests
* Revert "test only model load on petals"
This reverts commit 111cfa97f1
.
* move transformers and sentencetransformers to common env
* Share also transformers-musicgen
This commit is contained in:
parent
23eced1644
commit
b4b21a446b
23 changed files with 189 additions and 266 deletions
58
backend/python/petals/test_petals.py
Normal file
58
backend/python/petals/test_petals.py
Normal file
|
@ -0,0 +1,58 @@
|
|||
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="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()
|
Loading…
Add table
Add a link
Reference in a new issue