[Fix] Better error message when there is OOM during cache initialization (#203)

2023-06-22 15:30:06 +08:00
parent 14f0b39cda
commit 1d24ccb96c
2 changed files with 7 additions and 0 deletions
--- a/vllm/outputs.py
+++ b/vllm/outputs.py
@@ -53,6 +53,7 @@ class RequestOutput:
        prompt: The prompt string of the request.
        prompt_token_ids: The token IDs of the prompt.
        outputs: The output sequences of the request.
+        finished: Whether the whole request is finished.
    """
    def __init__(
        self,