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 14, 05:30 UTC
[Docs] Fix API Reference (#25140)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Sep 18, 2025 at 07:23 UTC
349e0e34627950db1cc4be0df9a0bc616e210589
1 file changed
+1
-1
mkdocs.yaml
+1
-1
@@ -79,7 +79,7 @@ plugins:
79
- "re:vllm\\._.*" # Internal modules
80
- "vllm.third_party"
81
- "vllm.vllm_flash_attn"
82
- - !ENV [API_AUTONAV_EXCLUDE, ""]
82
+ - !ENV [API_AUTONAV_EXCLUDE, "re:^$"] # Match nothing by default
83
- mkdocstrings:
84
handlers:
85
python: