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] Fixing requirements.txt (#3865)
Noam Gat committed
Apr 5, 2024 at 09:46 UTC
9edec652e2adfee7c06483271f5df4b1be1bfddc
1 file changed
+1
-1
requirements.txt
+1
-1
@@ -17,4 +17,4 @@ pynvml == 11.5.0
17
triton >= 2.1.0
18
outlines == 0.0.34
19
tiktoken == 0.6.0 # Required for DBRX tokenizer
20
-vllm-nccl-cu12>=2.18<2.19 # for downloading nccl library
20
+vllm-nccl-cu12>=2.18,<2.19 # for downloading nccl library