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, 11:00 UTC
Only depend on importlib-metadata for Python < 3.10 (#17776)
Signed-off-by: Christian Heimes <christian@python.org>
Christian Heimes committed
May 7, 2025 at 16:51 UTC
1a6af1453d2077832c3d5e8bcd60a5ef6a95e46b
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -29,7 +29,7 @@ partial-json-parser # used for parsing partial JSON outputs
29
pyzmq >= 25.0.0
30
msgspec
31
gguf >= 0.13.0
32
-importlib_metadata
32
+importlib_metadata; python_version < '3.10'
33
mistral_common[opencv] >= 1.5.4
34
opencv-python-headless >= 4.11.0 # required for video IO
35
pyyaml