Unverified Commit 3b7c20a6 authored by Kenichi Maehashi's avatar Kenichi Maehashi Committed by GitHub
Browse files

[Bugfix] Apply same sampling parameters for both `n=1` and `n>1` (#26005)


Signed-off-by: default avatarKenichi Maehashi <maehashi@preferred.jp>
parent f9e71481
......@@ -290,7 +290,7 @@ class AsyncLLM(EngineClient):
return queue
# Fan out child requests (for n>1).
parent_request = ParentRequest(request_id, params)
parent_request = ParentRequest(request_id, request.sampling_params)
for idx in range(params.n):
request_id, params = parent_request.get_child_info(idx)
child_request = request if idx == params.n - 1 else copy(request)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment