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
[BugFix]: set outlines pkg version (#6262)
Lim Xiang Yang committed
Jul 11, 2024 at 12:37 UTC
fc17110bbef4e78703abffac51133a2fb71e9f79
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -18,7 +18,7 @@ prometheus_client >= 0.18.0
18
prometheus-fastapi-instrumentator >= 7.0.0
19
tiktoken >= 0.6.0 # Required for DBRX tokenizer
20
lm-format-enforcer == 0.10.1
21
-outlines >= 0.0.43 # Requires torch >= 2.1.0
21
+outlines >= 0.0.43, < 0.1 # Requires torch >= 2.1.0
22
typing_extensions
23
filelock >= 3.10.4 # filelock starts to support `mode` argument from 3.10.4
24
pyzmq