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 16, 09:30 UTC
[Bugfix] Steaming continuous_usage_stats default to False (#9709)
Signed-off-by: Sam Stoelinga <sammiestoel@gmail.com>
Sam Stoelinga committed
Oct 25, 2024 at 22:05 UTC
067e77f9a87c3466fce41c8fe8710fddc69ec26c
1 file changed
+1
-1
vllm/entrypoints/openai/protocol.py
+1
-1
@@ -127,7 +127,7 @@ class ResponseFormat(OpenAIBaseModel):
127
128
class StreamOptions(OpenAIBaseModel):
129
include_usage: Optional[bool] = True
130
- continuous_usage_stats: Optional[bool] = True
130
+ continuous_usage_stats: Optional[bool] = False
131
132
133
class FunctionDefinition(OpenAIBaseModel):