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, 18:15 UTC
[Bugfix] Mirror jinja2 in pyproject.toml (#7723)
sasha0552 committed
Aug 21, 2024 at 13:41 UTC
dd3fa0e43055cc5dd8597b74afed7294132c79c5
1 file changed
+1
pyproject.toml
+1
@@ -7,6 +7,7 @@ requires = [
7
"setuptools >= 49.4.0",
8
"torch == 2.4.0",
9
"wheel",
10
+ "jinja2",
11
]
12
build-backend = "setuptools.build_meta"
13