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
[Misc][Bugfix] Update transformers for tokenizer issue (#6364)
Roger Wang committed
Jul 12, 2024 at 01:40 UTC
f7160d946a0a07703e72d81ba9ecf3913f192605
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -6,7 +6,7 @@ numpy < 2.0.0
6
requests
7
tqdm
8
py-cpuinfo
9
-transformers >= 4.42.0 # Required for Gemma 2 and for additional chat template parameters.
9
+transformers >= 4.42.4 # Required for Gemma 2 and for additional chat template parameters.
10
tokenizers >= 0.19.1 # Required for Llama 3.
11
fastapi
12
aiohttp