Unverified Commit 84683fa2 authored by XiaobingZhang's avatar XiaobingZhang Committed by GitHub
Browse files

[Bugfix] Offline example of disaggregated prefill (#13214)

parent 06767826
......@@ -22,7 +22,7 @@ def run_prefill(prefill_done):
# and 3 and do prefilling on request 2.
prompts = [
"Hello, my name is",
# "Hi, your name is",
"Hi, your name is",
# The decode node will actually "prefill" this request.
"Tell me a very long story",
]
......
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