chore: move benchmarking related code (#3406)

# What does this PR do?
- moving things and some formatting changes


## Test Plan

benchmarking/k8s-benchmark/README.md

@@ -34,13 +34,12 @@ This data enables data-driven architectural decisions and performance optimizati
 
 **1. Deploy base k8s infrastructure:**
 ```bash
-cd ../k8s
+cd ../../docs/source/distributions/k8s
 ./apply.sh
 ```
 
 **2. Deploy benchmark components:**
 ```bash
-cd ../k8s-benchmark
 ./apply.sh
 ```
 
@@ -56,7 +55,6 @@ kubectl get pods
 
 **Benchmark Llama Stack (default):**
 ```bash
-cd docs/source/distributions/k8s-benchmark/
 ./run-benchmark.sh
 ```
 

benchmarking/k8s-benchmark/benchmark.py

@@ -14,7 +14,7 @@ import os
 import random
 import statistics
 import time
-from typing import Tuple
+
 import aiohttp
 
 
@@ -57,9 +57,9 @@ class BenchmarkStats:
         success_rate = (self.success_count / self.total_requests) * 100
 
         print(f"\n{'=' * 60}")
-        print(f"BENCHMARK RESULTS")
+        print("BENCHMARK RESULTS")
 
-        print(f"\nResponse Time Statistics:")
+        print("\nResponse Time Statistics:")
         print(f"  Mean: {statistics.mean(self.response_times):.3f}s")
         print(f"  Median: {statistics.median(self.response_times):.3f}s")
         print(f"  Min: {min(self.response_times):.3f}s")
@@ -70,14 +70,14 @@ class BenchmarkStats:
 
         percentiles = [50, 90, 95, 99]
         sorted_times = sorted(self.response_times)
-        print(f"\nPercentiles:")
+        print("\nPercentiles:")
         for p in percentiles:
             idx = int(len(sorted_times) * p / 100) - 1
             idx = max(0, min(idx, len(sorted_times) - 1))
             print(f"  P{p}: {sorted_times[idx]:.3f}s")
 
         if self.ttft_times:
-            print(f"\nTime to First Token (TTFT) Statistics:")
+            print("\nTime to First Token (TTFT) Statistics:")
             print(f"  Mean: {statistics.mean(self.ttft_times):.3f}s")
             print(f"  Median: {statistics.median(self.ttft_times):.3f}s")
             print(f"  Min: {min(self.ttft_times):.3f}s")
@@ -87,14 +87,14 @@ class BenchmarkStats:
                 print(f"  Std Dev: {statistics.stdev(self.ttft_times):.3f}s")
 
             sorted_ttft = sorted(self.ttft_times)
-            print(f"\nTTFT Percentiles:")
+            print("\nTTFT Percentiles:")
             for p in percentiles:
                 idx = int(len(sorted_ttft) * p / 100) - 1
                 idx = max(0, min(idx, len(sorted_ttft) - 1))
                 print(f"  P{p}: {sorted_ttft[idx]:.3f}s")
 
         if self.chunks_received:
-            print(f"\nStreaming Statistics:")
+            print("\nStreaming Statistics:")
             print(f"  Mean chunks per response: {statistics.mean(self.chunks_received):.1f}")
             print(f"  Total chunks received: {sum(self.chunks_received)}")
 
@@ -108,14 +108,14 @@ class BenchmarkStats:
         print(f"Requests per second: {self.success_count / total_time:.2f}")
 
         if self.errors:
-            print(f"\nErrors (showing first 5):")
+            print("\nErrors (showing first 5):")
             for error in self.errors[:5]:
                 print(f"  {error}")
 
 
 class LlamaStackBenchmark:
     def __init__(self, base_url: str, model_id: str):
-        self.base_url = base_url.rstrip('/')
+        self.base_url = base_url.rstrip("/")
         self.model_id = model_id
         self.headers = {"Content-Type": "application/json"}
         self.test_messages = [
@@ -126,20 +126,14 @@ class LlamaStackBenchmark:
             [
                 {"role": "user", "content": "What is machine learning?"},
                 {"role": "assistant", "content": "Machine learning is a subset of AI..."},
-                {"role": "user", "content": "Can you give me a practical example?"}
+                {"role": "user", "content": "Can you give me a practical example?"},
-            ]
+            ],
         ]
 
-
+    async def make_async_streaming_request(self) -> tuple[float, int, float | None, str | None]:
-    async def make_async_streaming_request(self) -> Tuple[float, int, float | None, str | None]:
         """Make a single async streaming chat completion request."""
         messages = random.choice(self.test_messages)
-        payload = {
+        payload = {"model": self.model_id, "messages": messages, "stream": True, "max_tokens": 100}
-            "model": self.model_id,
-            "messages": messages,
-            "stream": True,
-            "max_tokens": 100
-        }
 
         start_time = time.time()
         chunks_received = 0
@@ -153,17 +147,17 @@ class LlamaStackBenchmark:
                 f"{self.base_url}/chat/completions",
                 headers=self.headers,
                 json=payload,
-                timeout=aiohttp.ClientTimeout(total=30)
+                timeout=aiohttp.ClientTimeout(total=30),
             ) as response:
                 if response.status == 200:
                     async for line in response.content:
                         if line:
-                            line_str = line.decode('utf-8').strip()
+                            line_str = line.decode("utf-8").strip()
-                            if line_str.startswith('data: '):
+                            if line_str.startswith("data: "):
                                 chunks_received += 1
                                 if ttft is None:
                                     ttft = time.time() - start_time
-                                if line_str == 'data: [DONE]':
+                                if line_str == "data: [DONE]":
                                     break
 
                     if chunks_received == 0:
@@ -180,7 +174,6 @@ class LlamaStackBenchmark:
         response_time = time.time() - start_time
         return response_time, chunks_received, ttft, error
 
-
     async def run_benchmark(self, duration: int, concurrent_users: int) -> BenchmarkStats:
         """Run benchmark using async requests for specified duration."""
         stats = BenchmarkStats()
@@ -192,7 +185,7 @@ class LlamaStackBenchmark:
         print(f"Model: {self.model_id}")
 
         connector = aiohttp.TCPConnector(limit=concurrent_users)
-        async with aiohttp.ClientSession(connector=connector) as session:
+        async with aiohttp.ClientSession(connector=connector):
 
             async def worker(worker_id: int):
                 """Worker that sends requests sequentially until canceled."""
@@ -216,7 +209,9 @@ class LlamaStackBenchmark:
                         await asyncio.sleep(1)  # Report every second
                         if time.time() >= last_report_time + 10:  # Report every 10 seconds
                             elapsed = time.time() - stats.start_time
-                            print(f"Completed: {stats.total_requests} requests in {elapsed:.1f}s, RPS: {stats.total_requests / elapsed:.1f}")
+                            print(
+                                f"Completed: {stats.total_requests} requests in {elapsed:.1f}s, RPS: {stats.total_requests / elapsed:.1f}"
+                            )
                             last_report_time = time.time()
                     except asyncio.CancelledError:
                         break
@@ -241,14 +236,16 @@ class LlamaStackBenchmark:
 
 def main():
     parser = argparse.ArgumentParser(description="Llama Stack Benchmark Tool")
-    parser.add_argument("--base-url", default=os.getenv("BENCHMARK_BASE_URL", "http://localhost:8000/v1/openai/v1"),
+    parser.add_argument(
-                       help="Base URL for the API (default: http://localhost:8000/v1/openai/v1)")
+        "--base-url",
-    parser.add_argument("--model", default=os.getenv("INFERENCE_MODEL", "test-model"),
+        default=os.getenv("BENCHMARK_BASE_URL", "http://localhost:8000/v1/openai/v1"),
-                       help="Model ID to use for requests")
+        help="Base URL for the API (default: http://localhost:8000/v1/openai/v1)",
-    parser.add_argument("--duration", type=int, default=60,
+    )
-                       help="Duration in seconds to run benchmark (default: 60)")
+    parser.add_argument(
-    parser.add_argument("--concurrent", type=int, default=10,
+        "--model", default=os.getenv("INFERENCE_MODEL", "test-model"), help="Model ID to use for requests"
-                       help="Number of concurrent users (default: 10)")
+    )
+    parser.add_argument("--duration", type=int, default=60, help="Duration in seconds to run benchmark (default: 60)")
+    parser.add_argument("--concurrent", type=int, default=10, help="Number of concurrent users (default: 10)")
 
     args = parser.parse_args()
 

benchmarking/k8s-benchmark/openai-mock-server.py

@@ -11,16 +11,18 @@ OpenAI-compatible mock server that returns:
 - Valid OpenAI-formatted chat completion responses with dynamic content
 """
 
-from flask import Flask, request, jsonify, Response
-import time
-import random
-import uuid
-import json
 import argparse
+import json
 import os
+import random
+import time
+import uuid
+
+from flask import Flask, Response, jsonify, request
 
 app = Flask(__name__)
 
+
 # Models from environment variables
 def get_models():
     models_str = os.getenv("MOCK_MODELS", "meta-llama/Llama-3.2-3B-Instruct")
@@ -29,40 +31,72 @@ def get_models():
     return {
         "object": "list",
         "data": [
-            {
+            {"id": model_id, "object": "model", "created": 1234567890, "owned_by": "vllm"} for model_id in model_ids
-                "id": model_id,
+        ],
-                "object": "model",
-                "created": 1234567890,
-                "owned_by": "vllm"
-            }
-            for model_id in model_ids
-        ]
     }
 
+
 def generate_random_text(length=50):
     """Generate random but coherent text for responses."""
     words = [
-        "Hello", "there", "I'm", "an", "AI", "assistant", "ready", "to", "help", "you",
+        "Hello",
-        "with", "your", "questions", "and", "tasks", "today", "Let", "me","know", "what",
+        "there",
-        "you'd", "like", "to", "discuss", "or", "explore", "together", "I", "can", "assist",
+        "I'm",
-        "with", "various", "topics", "including", "coding", "writing", "analysis", "and", "more"
+        "an",
+        "AI",
+        "assistant",
+        "ready",
+        "to",
+        "help",
+        "you",
+        "with",
+        "your",
+        "questions",
+        "and",
+        "tasks",
+        "today",
+        "Let",
+        "me",
+        "know",
+        "what",
+        "you'd",
+        "like",
+        "to",
+        "discuss",
+        "or",
+        "explore",
+        "together",
+        "I",
+        "can",
+        "assist",
+        "with",
+        "various",
+        "topics",
+        "including",
+        "coding",
+        "writing",
+        "analysis",
+        "and",
+        "more",
     ]
     return " ".join(random.choices(words, k=length))
 
-@app.route('/v1/models', methods=['GET'])
+
+@app.route("/v1/models", methods=["GET"])
 def list_models():
     models = get_models()
     print(f"[MOCK] Returning models: {[m['id'] for m in models['data']]}")
     return jsonify(models)
 
-@app.route('/v1/chat/completions', methods=['POST'])
+
+@app.route("/v1/chat/completions", methods=["POST"])
 def chat_completions():
     """Return OpenAI-formatted chat completion responses."""
     data = request.get_json()
-    default_model = get_models()['data'][0]['id']
+    default_model = get_models()["data"][0]["id"]
-    model = data.get('model', default_model)
+    model = data.get("model", default_model)
-    messages = data.get('messages', [])
+    messages = data.get("messages", [])
-    stream = data.get('stream', False)
+    stream = data.get("stream", False)
 
     print(f"[MOCK] Chat completion request - model: {model}, stream: {stream}")
 
@@ -71,11 +105,12 @@ def chat_completions():
     else:
         return handle_non_streaming_completion(model, messages)
 
+
 def handle_non_streaming_completion(model, messages):
     response_text = generate_random_text(random.randint(20, 80))
 
     # Calculate realistic token counts
-    prompt_tokens = sum(len(str(msg.get('content', '')).split()) for msg in messages)
+    prompt_tokens = sum(len(str(msg.get("content", "")).split()) for msg in messages)
     completion_tokens = len(response_text.split())
 
     response = {
@@ -83,25 +118,17 @@ def handle_non_streaming_completion(model, messages):
         "object": "chat.completion",
         "created": int(time.time()),
         "model": model,
-        "choices": [
+        "choices": [{"index": 0, "message": {"role": "assistant", "content": response_text}, "finish_reason": "stop"}],
-            {
-                "index": 0,
-                "message": {
-                    "role": "assistant",
-                    "content": response_text
-                },
-                "finish_reason": "stop"
-            }
-        ],
         "usage": {
             "prompt_tokens": prompt_tokens,
             "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens
+            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        },
     }
 
     return jsonify(response)
 
+
 def handle_streaming_completion(model, messages):
     def generate_stream():
         # Generate response text
@@ -114,12 +141,7 @@ def handle_streaming_completion(model, messages):
             "object": "chat.completion.chunk",
             "created": int(time.time()),
             "model": model,
-            "choices": [
+            "choices": [{"index": 0, "delta": {"role": "assistant", "content": ""}}],
-                {
-                    "index": 0,
-                    "delta": {"role": "assistant", "content": ""}
-                }
-            ]
         }
         yield f"data: {json.dumps(initial_chunk)}\n\n"
 
@@ -130,12 +152,7 @@ def handle_streaming_completion(model, messages):
                 "object": "chat.completion.chunk",
                 "created": int(time.time()),
                 "model": model,
-                "choices": [
+                "choices": [{"index": 0, "delta": {"content": f"{word} " if i < len(words) - 1 else word}}],
-                    {
-                        "index": 0,
-                        "delta": {"content": f"{word} " if i < len(words) - 1 else word}
-                    }
-                ]
             }
             yield f"data: {json.dumps(chunk)}\n\n"
             # Configurable delay to simulate realistic streaming
@@ -148,35 +165,30 @@ def handle_streaming_completion(model, messages):
             "object": "chat.completion.chunk",
             "created": int(time.time()),
             "model": model,
-            "choices": [
+            "choices": [{"index": 0, "delta": {"content": ""}, "finish_reason": "stop"}],
-                {
-                    "index": 0,
-                    "delta": {"content": ""},
-                    "finish_reason": "stop"
-                }
-            ]
         }
         yield f"data: {json.dumps(final_chunk)}\n\n"
         yield "data: [DONE]\n\n"
 
     return Response(
         generate_stream(),
-        mimetype='text/event-stream',
+        mimetype="text/event-stream",
         headers={
-            'Cache-Control': 'no-cache',
+            "Cache-Control": "no-cache",
-            'Connection': 'keep-alive',
+            "Connection": "keep-alive",
-            'Access-Control-Allow-Origin': '*',
+            "Access-Control-Allow-Origin": "*",
-        }
+        },
     )
 
-@app.route('/health', methods=['GET'])
+
+@app.route("/health", methods=["GET"])
 def health():
     return jsonify({"status": "healthy", "type": "openai-mock"})
 
-if __name__ == '__main__':
+
-    parser = argparse.ArgumentParser(description='OpenAI-compatible mock server')
+if __name__ == "__main__":
-    parser.add_argument('--port', type=int, default=8081, 
+    parser = argparse.ArgumentParser(description="OpenAI-compatible mock server")
-                       help='Port to run the server on (default: 8081)')
+    parser.add_argument("--port", type=int, default=8081, help="Port to run the server on (default: 8081)")
     args = parser.parse_args()
 
     port = args.port
@@ -187,4 +199,4 @@ if __name__ == '__main__':
     print("- OpenAI-formatted chat/completion responses with dynamic content")
     print("- Streaming support with valid SSE format")
     print(f"- Listening on: http://0.0.0.0:{port}")
-    app.run(host='0.0.0.0', port=port, debug=False)
+    app.run(host="0.0.0.0", port=port, debug=False)

docs/source/contributing/index.md

@@ -35,5 +35,5 @@ testing/record-replay
 
 ### Benchmarking
 
-```{include} ../../../docs/source/distributions/k8s-benchmark/README.md
+```{include} ../../../benchmarking/k8s-benchmark/README.md
 ```