mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 10:35:01 +00:00
feat: 🐍 add mamba support (#1589)
feat(mamba): Initial import This is a first iteration of the mamba backend, loosely based on mamba-chat(https://github.com/havenhq/mamba-chat).
This commit is contained in:
parent
52c9a7f45d
commit
9e653d6abe
13 changed files with 762 additions and 3 deletions
76
backend/python/mamba/test_backend_mamba.py
Normal file
76
backend/python/mamba/test_backend_mamba.py
Normal 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_vllm.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="facebook/opt-125m"))
|
||||
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="facebook/opt-125m"))
|
||||
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()
|
Loading…
Add table
Add a link
Reference in a new issue