You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -122,6 +122,7 @@ For more details see the <a href="https://docs.vllm.ai/en/stable/getting_started
122
122
-`tokenizers-cache-dir`: the directory for caching tokenizers
123
123
-`hash-seed`: seed for hash generation (if not set, is read from PYTHONHASHSEED environment variable)
124
124
-`zmq-endpoint`: ZMQ address to publish events
125
+
-`zmq-max-connect-attempts`: the maximum number of ZMQ connection attempts. defaults to 0. maximum: 10
125
126
-`event-batch-size`: the maximum number of kv-cache events to be sent together, defaults to 16
126
127
-`fake-metrics`: represents a predefined set of metrics to be sent to Prometheus as a substitute for the actual data. When specified, only these fake metrics will be reported — real metrics and fake metrics will never be reported simultaneously. The set should include values for
0 commit comments