@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / fe7d648fe5
Fork 0

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 17, 03:00 UTC

Don't show default value for flags in `EngineArgs` (#4223)

Co-authored-by: Harry Mellor <hmellor@oxts.com>

Harry Mellor committed Apr 21, 2024 at 17:15 UTC fe7d648fe56c138811e9b2b02937b55a84830454
1 file changed +3 -1
docs/source/models/engine_args.rst
+3 -1
@@ -9,6 +9,7 @@ Below, you can find an explanation of every engine argument for vLLM:
9 :module: vllm.engine.arg_utils
10 :func: _engine_args_parser
11 :prog: -m vllm.entrypoints.openai.api_server
12 + :nodefaultconst:
13
14 Async Engine Arguments
15 ----------------------
@@ -18,4 +19,5 @@ Below are the additional arguments related to the asynchronous engine:
19 .. argparse::
20 :module: vllm.engine.arg_utils
21 :func: _async_engine_args_parser
21 - :prog: -m vllm.entrypoints.openai.api_server
\ No newline at end of file
22 + :prog: -m vllm.entrypoints.openai.api_server
23 + :nodefaultconst:
\ No newline at end of file