更新README.md，修改Docker镜像版本，调整环境变量格式，优化基准测试脚本，添加新的基准测试功能，删除不再使用的示例文件。

benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py

+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import os
+
+import aiohttp
+from quart import Quart, make_response, request
+
+AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
+
+app = Quart(__name__)
+
+
+async def forward_request(url, data):
+    async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
+        headers = {"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"}
+        async with session.post(url=url, json=data, headers=headers) as response:
+            if response.status == 200:
+                # if response.headers.get('Transfer-Encoding') == 'chunked':
+                if True:
+                    async for chunk_bytes in response.content.iter_chunked(1024):
+                        yield chunk_bytes
+                else:
+                    content = await response.read()
+                    yield content
+
+
+@app.route("/v1/completions", methods=["POST"])
+async def handle_request():
+    try:
+        original_request_data = await request.get_json()
+
+        prefill_request = original_request_data.copy()
+        # change max_tokens = 1 to let it only do prefill
+        prefill_request["max_tokens"] = 1
+
+        # finish prefill
+        async for _ in forward_request(
+            "http://localhost:8100/v1/completions", prefill_request
+        ):
+            continue
+
+        # return decode
+        generator = forward_request(
+            "http://localhost:8200/v1/completions", original_request_data
+        )
+        response = await make_response(generator)
+        response.timeout = None
+
+        return response
+
+    except Exception as e:
+        import sys
+        import traceback
+
+        exc_info = sys.exc_info()
+        print("Error occurred in disagg prefill proxy server")
+        print(e)
+        print("".join(traceback.format_exception(*exc_info)))
+
+
+if __name__ == "__main__":
+    app.run(port=8000)

benchmarks/disagg_benchmarks/round_robin_proxy.py

+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import asyncio
+import itertools
+
+import aiohttp
+from aiohttp import web
+
+
+class RoundRobinProxy:
+    def __init__(self, target_ports):
+        self.target_ports = target_ports
+        self.port_cycle = itertools.cycle(self.target_ports)
+
+    async def handle_request(self, request):
+        target_port = next(self.port_cycle)
+        target_url = f"http://localhost:{target_port}{request.path_qs}"
+
+        async with aiohttp.ClientSession() as session:
+            try:
+                # Forward the request
+                async with session.request(
+                    method=request.method,
+                    url=target_url,
+                    headers=request.headers,
+                    data=request.content,
+                ) as response:
+                    # Start sending the response
+                    resp = web.StreamResponse(
+                        status=response.status, headers=response.headers
+                    )
+                    await resp.prepare(request)
+
+                    # Stream the response content
+                    async for chunk in response.content.iter_any():
+                        await resp.write(chunk)
+
+                    await resp.write_eof()
+                    return resp
+
+            except Exception as e:
+                return web.Response(text=f"Error: {str(e)}", status=500)
+
+
+async def main():
+    proxy = RoundRobinProxy([8100, 8200])
+    app = web.Application()
+    app.router.add_route("*", "/{path:.*}", proxy.handle_request)
+
+    runner = web.AppRunner(app)
+    await runner.setup()
+    site = web.TCPSite(runner, "localhost", 8000)
+    await site.start()
+
+    print("Proxy server started on http://localhost:8000")
+
+    # Keep the server running
+    await asyncio.Event().wait()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())