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, 13:30 UTC
Add `:markdownhelp:` to `EngineArgs` docs so markdown docstrings render properly (#17124)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Apr 24, 2025 at 18:28 UTC
0422ce109f3b4d80df073a542bd23d2c4b060873
2 files changed
+3
docs/source/serving/engine_args.md
+2
@@ -16,6 +16,7 @@ Below, you can find an explanation of every engine argument:
16
:func: _engine_args_parser
17
:prog: vllm serve
18
:nodefaultconst:
19
+ :markdownhelp:
20
```
21
22
## Async Engine Arguments
@@ -29,4 +30,5 @@ Additional arguments are available to the asynchronous engine which is used for
30
:func: _async_engine_args_parser
31
:prog: vllm serve
32
:nodefaultconst:
33
+ :markdownhelp:
34
```
requirements/docs.txt
+1
@@ -7,6 +7,7 @@ sphinx-togglebutton==0.3.2
7
myst-parser==3.0.1
8
msgspec
9
cloudpickle
10
+commonmark # Required by sphinx-argparse when using :markdownhelp:
11
12
# packages to install to build the documentation
13
cachetools