xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-26 11:47:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix comments

Browse Source 
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
This commit is contained in:
inkcherry 2025-12-22 02:59:45 +00:00
parent bba01338ca
commit 0b0c33d59e
2 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
examples/online_serving/disaggregated_serving/moriio_toy_proxy_server.py
View File

@ -195,8 +195,9 @@ def example_round_robin_dp_loader(request_number, dp_size):
@app.route("/v1/chat/completions", methods=["POST"]) @app.route("/v1/chat/completions", methods=["POST"])
async def handle_request(): async def handle_request():
try: try:
global request_nums with _list_lock:
request_nums += 1 global request_nums
request_nums += 1
def extract_ip_port_fast(url): def extract_ip_port_fast(url):
match = IP_PORT_PATTERN.search(url) match = IP_PORT_PATTERN.search(url)
@ -210,6 +211,10 @@ async def handle_request():
prefill_instance_endpoint = None prefill_instance_endpoint = None
decode_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) pid = request_nums % len(prefill_instances)
did = request_nums % len(decode_instances) did = request_nums % len(decode_instances)
prefill_instance_endpoint = prefill_instances[pid] prefill_instance_endpoint = prefill_instances[pid]
@ -291,8 +296,11 @@ async def handle_request():
response = await make_response(stream_generator) response = await make_response(stream_generator)
return response return response
except Exception as e: except Exception as e:
print(e) logger.exception("An error occurred while handling the request: %s", e)
pass return await make_response((
f"Internal Server Error: {e!s}",
500,
))
if __name__ == "__main__": if __name__ == "__main__":

2
vllm/distributed/kv_transfer/kv_connector/v1/moriio_connector.py
View File

@ -71,7 +71,7 @@ class MoRIIOConstants:
COMPLETION_PREFIX = "cmpl" COMPLETION_PREFIX = "cmpl"
PING_INTERVAL = 5 PING_INTERVAL = 5
MAX_PING_RETRIES = 1000000 MAX_PING_RETRIES = 100
DEFAULT_HANDSHAKE_PORT = "6301" DEFAULT_HANDSHAKE_PORT = "6301"
DEFAULT_NOTIFY_PORT = "61005" DEFAULT_NOTIFY_PORT = "61005"