minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Super tiny remove unneeded policy flag (#14608)

Browse Source
This commit is contained in:
fzyzcjy
2025-12-07 19:35:07 -08:00
committed by GitHub
parent 85d0ccfac0
commit 1915a1f8a7
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/router.md
+1 -2
View File
@@ -133,14 +133,13 @@ python -m sglang_router.launch_router \
> gRPC router supports both single-stage and PD serving. Provide `--tokenizer-path` or `--model-path` (HF repo or local directory) plus optional `--chat-template`. > gRPC router supports both single-stage and PD serving. Provide `--tokenizer-path` or `--model-path` (HF repo or local directory) plus optional `--chat-template`.
### Prefill/Decode Disaggregation ### Prefill/Decode Disaggregation
Split prefill and decode workers for PD-aware caching and balancing. Split prefill and decode workers for PD-aware caching and balancing. Specifying `--policy A` is equivalent to `--prefill-policy A --decode-policy A`.
```bash ```bash
python -m sglang_router.launch_router \ python -m sglang_router.launch_router \
--pd-disaggregation \ --pd-disaggregation \
--prefill http://prefill1:30001 9001 \ --prefill http://prefill1:30001 9001 \
--decode http://decode1:30011 \ --decode http://decode1:30011 \
--policy cache_aware \
--prefill-policy cache_aware \ --prefill-policy cache_aware \
--decode-policy power_of_two --decode-policy power_of_two
``` ```