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 11, 11:15 UTC
typing: Add type hints to TurnMetrics class in context.py (#30552)
Co-authored-by: zkexorability <zkexorability@gmail.com> Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
ゆり committed
Dec 15, 2025 at 16:00 UTC
33278073d68940dcaff579ab2dc316700e1db87a
1 file changed
+7
-7
vllm/entrypoints/context.py
+7
-7
@@ -74,24 +74,24 @@ class TurnMetrics:
74
75
def __init__(
76
self,
77
- input_tokens=0,
78
- output_tokens=0,
79
- cached_input_tokens=0,
80
- tool_output_tokens=0,
81
- ):
77
+ input_tokens: int = 0,
78
+ output_tokens: int = 0,
79
+ cached_input_tokens: int = 0,
80
+ tool_output_tokens: int = 0,
81
+ ) -> None:
82
self.input_tokens = input_tokens
83
self.output_tokens = output_tokens
84
self.cached_input_tokens = cached_input_tokens
85
self.tool_output_tokens = tool_output_tokens
86
87
- def reset(self):
87
+ def reset(self) -> None:
88
"""Reset counters for a new turn."""
89
self.input_tokens = 0
90
self.output_tokens = 0
91
self.cached_input_tokens = 0
92
self.tool_output_tokens = 0
93
94
- def copy(self):
94
+ def copy(self) -> "TurnMetrics":
95
"""Create a copy of this turn's token counts."""
96
return TurnMetrics(
97
self.input_tokens,