From 0b0c33d59ee576f335a61eec4e1f837969f01008 Mon Sep 17 00:00:00 2001 From: inkcherry Date: Mon, 22 Dec 2025 02:59:45 +0000 Subject: [PATCH] fix comments Signed-off-by: inkcherry --- .../moriio_toy_proxy_server.py | 16 ++++++++++++---- .../kv_connector/v1/moriio_connector.py | 2 +- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/examples/online_serving/disaggregated_serving/moriio_toy_proxy_server.py b/examples/online_serving/disaggregated_serving/moriio_toy_proxy_server.py index 67ef2b02c76a9..98481787268c6 100644 --- a/examples/online_serving/disaggregated_serving/moriio_toy_proxy_server.py +++ b/examples/online_serving/disaggregated_serving/moriio_toy_proxy_server.py @@ -195,8 +195,9 @@ def example_round_robin_dp_loader(request_number, dp_size): @app.route("/v1/chat/completions", methods=["POST"]) async def handle_request(): try: - global request_nums - request_nums += 1 + with _list_lock: + global request_nums + request_nums += 1 def extract_ip_port_fast(url): match = IP_PORT_PATTERN.search(url) @@ -210,6 +211,10 @@ async def handle_request(): prefill_instance_endpoint = None decode_instance_endpoint = None + if not prefill_instances or not decode_instances: + return await make_response( + ("Service Unavailable: No prefill or decode instances are registered.", + 503)) pid = request_nums % len(prefill_instances) did = request_nums % len(decode_instances) prefill_instance_endpoint = prefill_instances[pid] @@ -291,8 +296,11 @@ async def handle_request(): response = await make_response(stream_generator) return response except Exception as e: - print(e) - pass + logger.exception("An error occurred while handling the request: %s", e) + return await make_response(( + f"Internal Server Error: {e!s}", + 500, + )) if __name__ == "__main__": diff --git a/vllm/distributed/kv_transfer/kv_connector/v1/moriio_connector.py b/vllm/distributed/kv_transfer/kv_connector/v1/moriio_connector.py index 3cad26aeb84d4..1ce1f435cf544 100644 --- a/vllm/distributed/kv_transfer/kv_connector/v1/moriio_connector.py +++ b/vllm/distributed/kv_transfer/kv_connector/v1/moriio_connector.py @@ -71,7 +71,7 @@ class MoRIIOConstants: COMPLETION_PREFIX = "cmpl" PING_INTERVAL = 5 - MAX_PING_RETRIES = 1000000 + MAX_PING_RETRIES = 100 DEFAULT_HANDSHAKE_PORT = "6301" DEFAULT_NOTIFY_PORT = "61005"