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

Code structure refactor (#807)

Browse Source
This commit is contained in:
Liangsheng Yin
2024-07-29 23:04:48 -07:00
committed by GitHub
parent 21e22b9e96
commit cdcbde5fc3
41 changed files with 106 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/en/hyperparameter_tuning.md
View File

@@ -29,7 +29,7 @@ If OOM happens during prefill, try to decrease `--max-prefill-tokens`.
If OOM happens during decoding, try to decrease `--max-running-requests`.
You can also try to decrease `--mem-fraction-static`, which reduces the memory usage of the KV cache memory pool and helps both prefill and decoding.
### (Minor) Tune `--schedule-heuristic`
If you have many shared prefixes, use the default `--schedule-heuristic lpm`. `lpm` stands for longest prefix match.
### (Minor) Tune `--schedule-policy`
If you have many shared prefixes, use the default `--schedule-policy lpm`. `lpm` stands for longest prefix match.
When you have no shared prefixes at all or you always send the requests with the shared prefixes together,
you can try `--schedule-heuristic fcfs`. `fcfs` stands for first come first serve.
you can try `--schedule-policy fcfs`. `fcfs` stands for first come first serve.