feat: add autoscaling examples and repo cleanup

01_getting_started/.gitignore

@@ -0,0 +1 @@
+.flash/

01_getting_started/01_hello_world/README.md

@@ -33,7 +33,7 @@ Server starts at **http://localhost:8888**
 Visit **http://localhost:8888/docs** for interactive API documentation. QB endpoints are auto-generated by `flash run` based on your `@remote` functions.
 
 ```bash
-curl -X POST http://localhost:8888/gpu_worker/run_sync \
+curl -X POST http://localhost:8888/gpu_worker/runsync \
   -H "Content-Type: application/json" \
   -d '{"message": "Hello GPU!"}'
 ```

01_getting_started/01_hello_world/gpu_worker.py

@@ -13,7 +13,7 @@
 
 
 @remote(resource_config=gpu_config)
-async def gpu_hello(input_data: dict) -> dict:
+async def gpu_hello(payload: dict) -> dict:
     """Simple GPU worker that returns GPU hardware info."""
     import platform
     from datetime import datetime
@@ -25,7 +25,7 @@ async def gpu_hello(input_data: dict) -> dict:
     gpu_count = torch.cuda.device_count()
     gpu_memory = torch.cuda.get_device_properties(0).total_memory / (1024**3)
 
-    message = input_data.get("message", "Hello from GPU worker!")
+    message = payload.get("message", "Hello from GPU worker!")
 
     return {
         "status": "success",

01_getting_started/02_cpu_worker/.gitignore

@@ -46,3 +46,4 @@ uv.lock
 # OS
 .DS_Store
 Thumbs.db
+.flash/

01_getting_started/02_cpu_worker/README.md

@@ -33,7 +33,7 @@ Server starts at **http://localhost:8888**
 Visit **http://localhost:8888/docs** for interactive API documentation. QB endpoints are auto-generated by `flash run` based on your `@remote` functions.
 
 ```bash
-curl -X POST http://localhost:8888/cpu_worker/run_sync \
+curl -X POST http://localhost:8888/cpu_worker/runsync \
   -H "Content-Type: application/json" \
   -d '{"name": "Flash User"}'
 ```

01_getting_started/02_cpu_worker/cpu_worker.py

@@ -13,12 +13,12 @@
 
 
 @remote(resource_config=cpu_config)
-async def cpu_hello(input_data: dict) -> dict:
+async def cpu_hello(payload: dict) -> dict:
     """Simple CPU worker that returns a greeting."""
     import platform
     from datetime import datetime
 
-    message = f"Hello, {input_data.get('name', 'Anonymous Panda')}!"
+    message = f"Hello, {payload.get('name', 'Anonymous Panda')}!"
 
     return {
         "status": "success",

01_getting_started/03_mixed_workers/README.md

@@ -75,11 +75,11 @@ curl -X POST http://localhost:8888/classify \
   -d '{"text": "This product is amazing! I love it!"}'
 
 # Individual stages
-curl -X POST http://localhost:8888/cpu_worker/run_sync \
+curl -X POST http://localhost:8888/cpu_worker/runsync \
   -H "Content-Type: application/json" \
   -d '{"text": "Test message"}'
 
-curl -X POST http://localhost:8888/gpu_worker/run_sync \
+curl -X POST http://localhost:8888/gpu_worker/runsync \
   -H "Content-Type: application/json" \
   -d '{"cleaned_text": "Test message", "word_count": 2}'
 ```

01_getting_started/03_mixed_workers/cpu_worker.py

@@ -12,12 +12,12 @@
 
 
 @remote(resource_config=cpu_config)
-async def preprocess_text(input_data: dict) -> dict:
+async def preprocess_text(payload: dict) -> dict:
     """Preprocess text: cleaning and tokenization (cheap CPU work)."""
     import re
     from datetime import datetime
 
-    text = input_data.get("text", "")
+    text = payload.get("text", "")
 
     cleaned_text = text.strip()
     cleaned_text = re.sub(r"\s+", " ", cleaned_text)
@@ -39,13 +39,13 @@ async def preprocess_text(input_data: dict) -> dict:
 
 
 @remote(resource_config=cpu_config)
-async def postprocess_results(input_data: dict) -> dict:
+async def postprocess_results(payload: dict) -> dict:
     """Postprocess GPU results: formatting and aggregation (cheap CPU work)."""
     from datetime import datetime
 
-    predictions = input_data.get("predictions", [])
-    original_text = input_data.get("original_text", "")
-    metadata = input_data.get("metadata", {})
+    predictions = payload.get("predictions", [])
+    original_text = payload.get("original_text", "")
+    metadata = payload.get("metadata", {})
 
     if predictions:
         top_prediction = max(predictions, key=lambda x: x["confidence"])

01_getting_started/03_mixed_workers/gpu_worker.py

@@ -14,15 +14,15 @@
 
 
 @remote(resource_config=gpu_config, dependencies=["torch"])
-async def gpu_inference(input_data: dict) -> dict:
+async def gpu_inference(payload: dict) -> dict:
     """GPU inference: mock sentiment classification."""
     import random
     from datetime import datetime
 
     import torch
 
-    cleaned_text = input_data.get("cleaned_text", "")
-    word_count = input_data.get("word_count", 0)
+    cleaned_text = payload.get("cleaned_text", "")
+    word_count = payload.get("word_count", 0)
 
     gpu_available = torch.cuda.is_available()
     if gpu_available:

01_getting_started/03_mixed_workers/pipeline.py

@@ -34,3 +34,12 @@ async def classify(text: str) -> dict:
             },
         }
     )
+
+
+if __name__ == "__main__":
+    import asyncio
+
+    test_text = "This is a test message for the classification pipeline."
+    print(f"Testing classify with text: {test_text}")
+    result = asyncio.run(classify(test_text))
+    print(f"Result: {result}")

01_getting_started/04_dependencies/.gitignore

@@ -46,3 +46,4 @@ uv.lock
 # OS
 .DS_Store
 Thumbs.db
+.flash/

01_getting_started/04_dependencies/cpu_worker.py

@@ -29,7 +29,7 @@
         "matplotlib",
     ],
 )
-async def process_data(input_data: dict) -> dict:
+async def process_data(payload: dict) -> dict:
     """
     Worker with data science dependencies.
 
@@ -46,7 +46,7 @@ async def process_data(input_data: dict) -> dict:
     import pandas as pd
     import scipy
 
-    data = input_data.get("data", [[1, 2], [3, 4], [5, 6]])
+    data = payload.get("data", [[1, 2], [3, 4], [5, 6]])
 
     # Create DataFrame and compute statistics
     df = pd.DataFrame(data, columns=["A", "B"])
@@ -80,7 +80,7 @@ async def process_data(input_data: dict) -> dict:
 
 
 @remote(resource_config=minimal_config)  # No dependencies!
-async def minimal_process(input_data: dict) -> dict:
+async def minimal_process(payload: dict) -> dict:
     """
     Worker with NO external dependencies.
 
@@ -93,7 +93,7 @@ async def minimal_process(input_data: dict) -> dict:
     import re
     from datetime import datetime
 
-    text = input_data.get("text", "")
+    text = payload.get("text", "")
 
     # Built-in operations only
     word_count = len(text.split())

01_getting_started/04_dependencies/gpu_worker.py

@@ -29,7 +29,7 @@
         "numpy<2.0.0",  # Maximum version constraint
     ],
 )
-async def process_with_ml_libs(input_data: dict) -> dict:
+async def process_with_ml_libs(payload: dict) -> dict:
     """
     Worker with versioned Python dependencies.
 
@@ -74,7 +74,7 @@ async def process_with_ml_libs(input_data: dict) -> dict:
     dependencies=["opencv-python", "requests"],
     system_dependencies=["ffmpeg", "libgl1"],  # System packages via apt
 )
-async def process_with_system_deps(input_data: dict) -> dict:
+async def process_with_system_deps(payload: dict) -> dict:
     """
     Worker with system-level dependencies.
 

02_ml_inference/01_text_to_speech/README.md

@@ -43,14 +43,14 @@ Visit http://localhost:8888/docs for interactive API documentation. QB endpoints
 
 **Generate speech (JSON with base64 audio):**
 ```bash
-curl -X POST http://localhost:8888/gpu_worker/run_sync \
+curl -X POST http://localhost:8888/gpu_worker/runsync \
   -H "Content-Type: application/json" \
   -d '{"text": "Hello world!", "speaker": "Ryan", "language": "English"}'
 ```
 
 **List available voices:**
 ```bash
-curl -X POST http://localhost:8888/gpu_worker/run_sync \
+curl -X POST http://localhost:8888/gpu_worker/runsync \
   -H "Content-Type: application/json" \
   -d '{}'
 ```

02_ml_inference/01_text_to_speech/gpu_worker.py

@@ -23,7 +23,7 @@
         "soundfile",
     ],
 )
-async def generate_speech(input_data: dict) -> dict:
+async def generate_speech(payload: dict) -> dict:
     """
     Generate speech using Qwen3-TTS-12Hz-1.7B-CustomVoice model.
 
@@ -72,10 +72,10 @@ async def generate_speech(input_data: dict) -> dict:
         "Auto",
     ]
 
-    text = input_data.get("text", "Hello, this is a test.")
-    speaker = input_data.get("speaker", "Ryan")
-    language = input_data.get("language", "Auto")
-    instruct = input_data.get("instruct", "")
+    text = payload.get("text", "Hello, this is a test.")
+    speaker = payload.get("speaker", "Ryan")
+    language = payload.get("language", "Auto")
+    instruct = payload.get("instruct", "")
 
     if speaker not in valid_speakers:
         return {
@@ -133,7 +133,7 @@ async def generate_speech(input_data: dict) -> dict:
 
 
 @remote(resource_config=gpu_config, dependencies=["qwen-tts"])
-async def get_voices(input_data: dict) -> dict:
+async def get_voices(payload: dict) -> dict:
     """Get available voices and languages."""
     speakers = {
         "Vivian": "Bright, slightly edgy young female voice (Chinese native)",