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, 22:15 UTC
[Doc] arg_utils.py: fixed a typo (#13785)
Eli Boyarski committed
Feb 25, 2025 at 04:23 UTC
7196a3b1db4f6ce57d76baf23cef36effc7558dc
1 file changed
+1
-1
vllm/engine/arg_utils.py
+1
-1
@@ -382,7 +382,7 @@ class EngineArgs:
382
'https://github.com/noamgat/lm-format-enforcer.'
383
' Can be overridden per request via guided_decoding_backend'
384
' parameter.\n'
385
- 'Backend-sepcific options can be supplied in a comma-separated '
385
+ 'Backend-specific options can be supplied in a comma-separated '
386
'list following a colon after the backend name. Valid backends and '
387
'all available options are: [xgrammar:no-fallback, '
388
'outlines:no-fallback, lm-format-enforcer:no-fallback]')