server: fix bugs when running speculative decoding

This commit is contained in:
Li, Zonghang
2025-07-13 21:52:59 +08:00
parent b019a707b8
commit 86ca21e49c
2 changed files with 2 additions and 1 deletions
+1
View File
@@ -381,6 +381,7 @@ curl -X POST http://localhost:8080/v1/cancel \
```
**9. How to use speculative decoding?**
Please see "[Power prima.cpp with speculative decoding: Further speeds up by up to 80%](https://github.com/Lizonghang/prima.cpp/discussions/29)".
## ❤️ Acknowledgment