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
[Bugfix] Fix filelock version requirement (#4075)
Zhuohan Li committed
Apr 14, 2024 at 21:50 UTC
e11e2007368b22fce05b9ecdf00dd48eda471f9e
1 file changed
+2
-1
requirements-common.txt
+2
-1
@@ -12,4 +12,5 @@ pydantic >= 2.0 # Required for OpenAI server.
12
prometheus_client >= 0.18.0
13
tiktoken == 0.6.0 # Required for DBRX tokenizer
14
outlines == 0.0.34 # Requires torch >= 2.1.0
15
-typing_extensions
\ No newline at end of file
15
+typing_extensions
16
+filelock >= 3.10.4 # filelock starts to support `mode` argument from 3.10.4