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, 08:30 UTC
[Doc] Avoid documenting dynamic / internal modules (#18626)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 24, 2025 at 00:58 UTC
15b45ffb9accfbc160217d51232669ab6c3461be
1 file changed
+4
mkdocs.yaml
+4
@@ -60,6 +60,10 @@ plugins:
60
- api-autonav:
61
modules: ["vllm"]
62
api_root_uri: "api"
63
+ exclude:
64
+ - "re:vllm\\._.*" # Internal modules
65
+ - "vllm.third_party"
66
+ - "vllm.vllm_flash_attn"
67
- mkdocstrings:
68
handlers:
69
python: