extras: add vllm,bark,vall-e-x tests, bump diffusers (#1422)

* tests: add vllm

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

* tests: Add vall-e-x tests

* Add bark tests

* bump diffusers

---------

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

backend/python/bark/Makefile

@@ -3,3 +3,15 @@ ttsbark:
 	@echo "Creating virtual environment..."
 	@conda env create --name ttsbark --file ttsbark.yml
 	@echo "Virtual environment created."
+
+.PHONY: run
+run:
+	@echo "Running bark..."
+	bash run.sh
+	@echo "bark run."
+
+.PHONY: test
+test:
+	@echo "Testing bark..."
+	bash test.sh
+	@echo "bark tested."

backend/python/bark/test.py

@@ -0,0 +1,81 @@
+"""
+A test script to test the gRPC service
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    """
+    TestBackendServicer is the class that tests the gRPC service
+    """
+    def setUp(self):
+        """
+        This method sets up the gRPC service by starting the server
+        """
+        self.service = subprocess.Popen(["python3", "ttsbark.py", "--addr", "localhost:50051"])
+        time.sleep(10)
+
+    def tearDown(self) -> None:
+        """
+        This method tears down the gRPC service by terminating the server
+        """
+        self.service.terminate()
+        self.service.wait()
+
+    def test_server_startup(self):
+        """
+        This method tests if the server starts up successfully
+        """
+        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="v2/en_speaker_4"))
+                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_tts(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="v2/en_speaker_4"))
+                self.assertTrue(response.success)
+                tts_request = backend_pb2.TTSRequest(text="80s TV news production music hit for tonight's biggest story")
+                tts_response = stub.TTS(tts_request)
+                self.assertIsNotNone(tts_response)
+        except Exception as err:
+            print(err)
+            self.fail("TTS service failed")
+        finally:
+            self.tearDown()

backend/python/bark/test.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+##
+## A bash script wrapper that runs the bark server with conda
+
+# Activate conda environment
+source activate ttsbark
+
+# 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.py

backend/python/bark/test_ttsbark.py

@@ -1,32 +0,0 @@
-import unittest
-import subprocess
-import time
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-class TestBackendServicer(unittest.TestCase):
-    """
-    TestBackendServicer is the class that tests the gRPC service
-    """
-    def setUp(self):
-        self.service = subprocess.Popen(["python3", "ttsbark.py", "--addr", "localhost:50051"])
-
-    def tearDown(self) -> None:
-        self.service.terminate()
-        self.service.wait()
-
-    def test_server_startup(self):
-        time.sleep(2)
-        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()

backend/python/diffusers/diffusers.yml

@@ -25,15 +25,15 @@ dependencies:
   - xz=5.4.2=h5eee18b_0
   - zlib=1.2.13=h5eee18b_0
   - pip:
-      - accelerate==0.23.0
+      - accelerate>=0.11.0
       - certifi==2023.7.22
       - charset-normalizer==3.3.0
       - compel==2.0.2
-      - diffusers==0.21.4
+      - diffusers==0.24.0
       - filelock==3.12.4
       - fsspec==2023.9.2
       - grpcio==1.59.0
-      - huggingface-hub==0.17.3
+      - huggingface-hub>=0.19.4
       - idna==3.4
       - importlib-metadata==6.8.0
       - jinja2==3.1.2
@@ -63,10 +63,9 @@ dependencies:
       - requests==2.31.0
       - safetensors==0.4.0
       - sympy==1.12
-      - tokenizers==0.14.1
       - torch==2.1.0
       - tqdm==4.66.1
-      - transformers==4.34.0
+      - transformers>=4.25.1
       - triton==2.1.0
       - typing-extensions==4.8.0
       - urllib3==2.0.6

backend/python/transformers-musicgen/Makefile

@@ -17,7 +17,6 @@ run:
 	bash run.sh
 	@echo "transformers run."
 
-# It is not working well by using command line. It only6 works with IDE like VSCode.
 .PHONY: test
 test:
 	@echo "Testing transformers..."

backend/python/vall-e-x/Makefile

@@ -10,3 +10,9 @@ run:
 	@echo "Running ttsvalle..."
 	bash run.sh
 	@echo "ttsvalle run."
+
+.PHONY: test
+test:
+	@echo "Testing valle..."
+	bash test.sh
+	@echo "valle tested."

backend/python/vall-e-x/test.py

@@ -0,0 +1,81 @@
+"""
+A test script to test the gRPC service
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    """
+    TestBackendServicer is the class that tests the gRPC service
+    """
+    def setUp(self):
+        """
+        This method sets up the gRPC service by starting the server
+        """
+        self.service = subprocess.Popen(["python3", "ttsvalle.py", "--addr", "localhost:50051"])
+        time.sleep(10)
+
+    def tearDown(self) -> None:
+        """
+        This method tears down the gRPC service by terminating the server
+        """
+        self.service.terminate()
+        self.service.wait()
+
+    def test_server_startup(self):
+        """
+        This method tests if the server starts up successfully
+        """
+        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="dingzhen"))
+                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_tts(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="dingzhen"))
+                self.assertTrue(response.success)
+                tts_request = backend_pb2.TTSRequest(text="80s TV news production music hit for tonight's biggest story")
+                tts_response = stub.TTS(tts_request)
+                self.assertIsNotNone(tts_response)
+        except Exception as err:
+            print(err)
+            self.fail("TTS service failed")
+        finally:
+            self.tearDown()

backend/python/vall-e-x/test.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+##
+## A bash script wrapper that runs the ttsvalle server with conda
+
+# Activate conda environment
+source activate ttsvalle
+
+# 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.py

backend/python/vllm/Makefile

@@ -9,3 +9,9 @@ run:
 	@echo "Running vllm..."
 	bash run.sh
 	@echo "vllm run."
+
+.PHONY: test
+test:
+	@echo "Testing vllm..."
+	bash test.sh
+	@echo "vllm tested."

backend/python/vllm/test.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+##
+## A bash script wrapper that runs the transformers server with conda
+
+# Activate conda environment
+source activate vllm
+
+# 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_backend_vllm.py

backend/python/vllm/test_backend_vllm.py

@@ -21,13 +21,13 @@ class TestBackendServicer(unittest.TestCase):
     """
     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):
-        time.sleep(2)
         try:
             self.setUp()
             with grpc.insecure_channel("localhost:50051") as channel:
@@ -39,3 +39,38 @@ class TestBackendServicer(unittest.TestCase):
             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()