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, 04:15 UTC
Upgrade transformers to v4.38.0 (#2965)
Woosuk Kwon committed
Feb 21, 2024 at 09:38 UTC
c20ecb6a51cb58d408eb5ae7b03ac76c7b83e609
1 file changed
+1
-1
requirements.txt
+1
-1
@@ -4,7 +4,7 @@ ray >= 2.9
4
sentencepiece # Required for LLaMA tokenizer.
5
numpy
6
torch == 2.1.2
7
-transformers >= 4.37.0 # Required for Qwen2
7
+transformers >= 4.38.0 # Required for Gemma.
8
xformers == 0.0.23.post1 # Required for CUDA 12.1.
9
fastapi
10
uvicorn[standard]