EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Update hyperparameter_tuning.md (#918)

Browse Source
This commit is contained in:
Ying Sheng
2024-08-04 13:51:52 -07:00
committed by GitHub
parent 0d4f3a9fcd
commit 975adb802b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/en/hyperparameter_tuning.md
View File

@@ -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.