We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
n=1
n>1
1 parent f9e7148 commit 3b7c20aCopy full SHA for 3b7c20a
vllm/v1/engine/async_llm.py
@@ -290,7 +290,7 @@ async def add_request(
290
return queue
291
292
# Fan out child requests (for n>1).
293
- parent_request = ParentRequest(request_id, params)
+ parent_request = ParentRequest(request_id, request.sampling_params)
294
for idx in range(params.n):
295
request_id, params = parent_request.get_child_info(idx)
296
child_request = request if idx == params.n - 1 else copy(request)
0 commit comments