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 9, 13:33 UTC
[Doc] Improve serve parameter documentation with meaningful defaults (#33082)
Signed-off-by: Karan Bansal <karanb192@gmail.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Karan Bansal committed
Jan 27, 2026 at 22:49 UTC
a6760f152538c96d8f0c743b204e24c6fd860fa3
1 file changed
+2
-1
docs/mkdocs/hooks/generate_argparse.py
+2
-1
@@ -162,7 +162,8 @@ class MarkdownFormatter(HelpFormatter):
162
if action.help:
163
self._markdown_output.append(f"{action.help}\n\n")
164
165
- if (default := action.default) != SUPPRESS:
165
+ # None usually means the default is determined at runtime
166
+ if (default := action.default) != SUPPRESS and default is not None:
167
# Make empty string defaults visible
168
if default == "":
169
default = '""'