dfdffd

README.md

@@ -42,14 +42,13 @@ This is a Gradio deployment of [LLaMA-Omni](https://github.com/ictnlp/LLaMA-Omni
 
 3. Install fairseq:
    ```bash
-   git clone https://github.com/pytorch/fairseq
-   cd fairseq
-   pip install -e . --no-build-isolation
+   pip install git+https://github.com/pytorch/fairseq.git
    ```
 
-4. Install flash-attention:
+4. Install optional dependencies (if not on Mac M1/M2):
    ```bash
-   pip install flash-attn --no-build-isolation
+   # Only run this if not on Mac with Apple Silicon
+   pip install flash-attn
    ```
 
 ## 🚀 Deployment

app_gradio_spaces.py

@@ -51,7 +51,7 @@ def setup_environment():
     
     return "✅ Environment setup complete!"
 
-def start_services(controller_output, model_worker_output, web_server_output):
+def start_services():
     """Start the controller, model worker, and web server."""
     # Start the controller
     controller_process = run_background_process(
@@ -59,14 +59,6 @@ def start_services(controller_output, model_worker_output, web_server_output):
         "Controller"
     )
     
-    # Start a thread to read controller output
-    controller_thread = threading.Thread(
-        target=read_process_output,
-        args=(controller_process, controller_output, "Controller"),
-        daemon=True
-    )
-    controller_thread.start()
-    
     # Wait for controller to start
     time.sleep(5)
     
@@ -76,14 +68,6 @@ def start_services(controller_output, model_worker_output, web_server_output):
         "Model Worker"
     )
     
-    # Start a thread to read model worker output
-    model_worker_thread = threading.Thread(
-        target=read_process_output,
-        args=(model_worker_process, model_worker_output, "Model Worker"),
-        daemon=True
-    )
-    model_worker_thread.start()
-    
     # Wait for model worker to start
     time.sleep(10)
     
@@ -93,18 +77,10 @@ def start_services(controller_output, model_worker_output, web_server_output):
         "Web Server"
     )
     
-    # Start a thread to read web server output
-    web_server_thread = threading.Thread(
-        target=read_process_output,
-        args=(web_server_process, web_server_output, "Web Server"),
-        daemon=True
-    )
-    web_server_thread.start()
-    
     # Wait for web server to start
     time.sleep(5)
     
-    return "✅ All services started! Click the 'Open Interface' button below."
+    return "✅ All services started successfully! Click 'Open Interface' to access the application."
 
 def build_ui():
     """Build the Gradio UI."""
@@ -120,19 +96,17 @@ def build_ui():
             start_btn = gr.Button("Start LLaMA-Omni Services")
             status_output = gr.Textbox(label="Status", value="Click 'Start LLaMA-Omni Services' to begin.")
             
-            with gr.Accordion("Service Logs", open=False):
-                controller_output = gr.Markdown("Controller not started")
-                model_worker_output = gr.Markdown("Model Worker not started")
-                web_server_output = gr.Markdown("Web Server not started")
+            controller_output = gr.Markdown(value="Controller not started")
+            model_worker_output = gr.Markdown(value="Model Worker not started") 
+            web_server_output = gr.Markdown(value="Web Server not started")
             
             start_btn.click(
                 start_services,
-                inputs=[],
-                outputs=[status_output, controller_output, model_worker_output, web_server_output]
+                outputs=status_output
             )
             
             interface_btn = gr.Button("Open Interface")
-            interface_btn.click(lambda: gr.update(value="http://localhost:8001"), None, None)
+            interface_btn.click(lambda: gr.Redirect("http://localhost:8001"), None, None)
         
         with gr.Tab("About"):
             gr.Markdown("""
@@ -157,4 +131,4 @@ def build_ui():
 
 if __name__ == "__main__":
     demo = build_ui()
-    demo.launch(server_port=7860) 
+    demo.launch(server_name="0.0.0.0", server_port=7860) 

cog.yaml

@@ -3,6 +3,7 @@ build:
   python_version: "3.10"
   python_packages:
     - "torch==2.0.1"
+    - "numpy==1.24.0"
     - "transformers==4.34.0"
     - "accelerate==0.21.0"
     - "gradio==3.50.2"
@@ -10,9 +11,7 @@ build:
     - "uvicorn==0.23.2"
     - "pydantic==2.3.0"
     - "openai-whisper==20231117"
-    - "numpy==1.24.0"
     - "tqdm==4.66.1"
-    - "flash-attn==2.3.0"
     - "requests==2.31.0"
   system_packages:
     - "wget"
@@ -20,6 +19,7 @@ build:
     - "libsndfile1"
   run:
     - "pip install -e git+https://github.com/pytorch/fairseq.git#egg=fairseq"
+    - "if [ $(uname -m) != 'arm64' ] || [ $(uname -s) != 'Darwin' ]; then pip install flash-attn==2.3.0; fi"
     - "mkdir -p vocoder"
     - "wget https://dl.fbaipublicfiles.com/fairseq/speech_to_speech/vocoder/code_hifigan/mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj/g_00500000 -P vocoder/"
     - "wget https://dl.fbaipublicfiles.com/fairseq/speech_to_speech/vocoder/code_hifigan/mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj/config.json -P vocoder/"

pyproject.toml

@@ -16,15 +16,15 @@ readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
     "torch>=2.0.0",
+    "numpy>=1.24.0",
     "transformers>=4.34.0",
     "accelerate>=0.21.0",
     "gradio>=3.50.2",
     "fastapi>=0.104.0",
     "uvicorn>=0.23.2",
     "pydantic>=2.3.0",
-    "whisper>=0.0.1",
-    "numpy>=1.24.0",
+    "openai-whisper>=0.0.1",
     "tqdm>=4.66.1",
-    "flash-attn>=2.3.0",
+    "requests>=2.31.0",
     "fairseq>=0.12.2",
 ] 

requirements.txt

@@ -1,4 +1,5 @@
 torch>=2.0.0
+numpy>=1.24.0
 transformers>=4.34.0
 accelerate>=0.21.0
 gradio>=3.50.2
@@ -6,8 +7,7 @@ fastapi>=0.104.0
 uvicorn>=0.23.2
 pydantic>=2.3.0
 openai-whisper>=0.0.1
-numpy>=1.24.0
 tqdm>=4.66.1
+requests>=2.31.0
 git+https://github.com/pytorch/fairseq.git
-flash-attn>=2.3.0
-requests>=2.31.0 
+flash-attn>=2.3.0; platform_system != "Darwin" or platform_machine != "arm64"