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 11, 15:00 UTC
Fix typo of endpoint name in CLI args docs (#30473)
Signed-off-by: Kenichi Maehashi <maehashi@preferred.jp>
Kenichi Maehashi committed
Dec 11, 2025 at 20:07 UTC
853611bb181290787d05502568fe76837507fdd9
1 file changed
+1
-1
vllm/entrypoints/openai/cli_args.py
+1
-1
@@ -176,7 +176,7 @@ class FrontendArgs:
176
enable_force_include_usage: bool = False
177
"""If set to True, including usage on every request."""
178
enable_tokenizer_info_endpoint: bool = False
179
- """Enable the /get_tokenizer_info endpoint. May expose chat
179
+ """Enable the `/tokenizer_info` endpoint. May expose chat
180
templates and other tokenizer configuration."""
181
enable_log_outputs: bool = False
182
"""If True, log model outputs (generations).