Unverified Commit 975adb80 authored by Ying Sheng's avatar Ying Sheng Committed by GitHub
Browse files

Update hyperparameter_tuning.md (#918)

parent 0d4f3a9f
......@@ -10,7 +10,7 @@ When the server is running at full load, look for the following in the log:
### Tune Your Request Submission Speed
`#queue-req` indicates the number of requests in the queue. If you frequently see `#queue-req == 0`, it suggests you are bottlenecked by the request submission speed.
A healthy range for `#queue-req` is `100 - 3000`.
A healthy range for `#queue-req` is `100 - 1000`.
### Tune `--schedule-conservativeness`
`token usage` indicates the KV cache memory utilization of the server. `token usage > 0.9` means good utilization.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment