xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-26 19:25:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[FIX] Explain why the finished_reason of ignored sequences are length (#1289)

Browse Source
This commit is contained in:
Zhuohan Li 2023-10-08 15:22:38 -07:00 committed by GitHub
parent ee92b58b3a
commit 6b5296aa3a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/sequence.py
View File

@ -35,6 +35,9 @@ class SequenceStatus(enum.Enum):
elif status == SequenceStatus.FINISHED_ABORTED:
finish_reason = "abort"
elif status == SequenceStatus.FINISHED_IGNORED:
# The ignored sequences are the sequences whose prompt lengths
# are longer than the model's length cap. Therefore, the stop
# reason should also be "length" as in OpenAI API.
finish_reason = "length"
else:
finish_reason = None