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 16, 22:00 UTC
[Doc] Reinstate doc dependencies (#6061)
Cyrus Leung committed
Jul 2, 2024 at 18:53 UTC
31354e563f077888ff1efb8ba4dad530cbdadd32
1 file changed
+8
docs/requirements-docs.txt
+8
@@ -3,3 +3,11 @@ sphinx-book-theme==1.0.1
3
sphinx-copybutton==0.5.2
4
myst-parser==2.0.0
5
sphinx-argparse
6
+
7
+# packages to install to build the documentation
8
+pydantic
9
+-f https://download.pytorch.org/whl/cpu
10
+torch
11
+py-cpuinfo
12
+transformers
13
+openai # Required by docs/source/serving/openai_compatible_server.md's vllm.entrypoints.openai.cli_args