A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 06:00 UTC
[MISC] typo fix (#19672)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Jun 16, 2025 at 15:18 UTC
26bc46ef8954bac7f2387a83e6781655ea81782c
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -1794,7 +1794,7 @@ class ParallelConfig:
1794
"""The full name of the worker class to use. If "auto", the worker class
1795
will be determined based on the platform."""
1796
sd_worker_cls: str = "auto"
1797
- """The full name of the worker class to use for speculative decofing.
1797
+ """The full name of the worker class to use for speculative decoding.
1798
If "auto", the worker class will be determined based on the platform."""
1799
worker_extension_cls: str = ""
1800
"""The full name of the worker extension class to use. The worker extension