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, 23:15 UTC
[build][misc] limit numpy version (#5582)
youkaichao committed
Jun 16, 2024 at 16:07 UTC
f07d5133202c08899eb5f51134af0f43b7791a33
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -2,7 +2,7 @@ cmake >= 3.21
2
ninja # For faster builds.
3
psutil
4
sentencepiece # Required for LLaMA tokenizer.
5
-numpy
5
+numpy < 2.0.0
6
requests
7
py-cpuinfo
8
transformers >= 4.40.0 # Required for StarCoder2 & Llava, Llama 3.