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, 09:45 UTC
[MISC] fix typo (#18305)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
May 18, 2025 at 01:52 UTC
66e63e86ecd650f40ece667851f08de5378d6d1b
1 file changed
+2
-2
vllm/usage/usage_lib.py
+2
-2
@@ -161,7 +161,7 @@ class UsageMessage:
161
usage_context: UsageContext,
162
extra_kvs: dict[str, Any]) -> None:
163
self._report_usage_once(model_architecture, usage_context, extra_kvs)
164
- self._report_continous_usage()
164
+ self._report_continuous_usage()
165
166
def _report_usage_once(self, model_architecture: str,
167
usage_context: UsageContext,
@@ -219,7 +219,7 @@ class UsageMessage:
219
self._write_to_file(data)
220
self._send_to_server(data)
221
222
- def _report_continous_usage(self):
222
+ def _report_continuous_usage(self):
223
"""Report usage every 10 minutes.
224
225
This helps us to collect more data points for uptime of vLLM usages.