A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 18:30 UTC
simple bugfix: Update stats.py (#15139)
Wang Ran (汪然) committed
Mar 20, 2025 at 02:26 UTC
8310e0b59b412693831e7b8e6fa11fc13698e17c
1 file changed
+1
-1
vllm/v1/metrics/stats.py
+1
-1
@@ -6,7 +6,7 @@ from typing import TYPE_CHECKING, Optional
6
7
if TYPE_CHECKING:
8
from vllm.v1.engine import EngineCoreEvent, EngineCoreOutput, FinishReason
9
- from vllm.v1.output_processor import RequestState
9
+ from vllm.v1.engine.output_processor import RequestState
10
11
12
@dataclass