diff --git a/benchmarks/launch_tgi_server.sh b/benchmarks/launch_tgi_server.sh index f491c90d0683e..8c5cd454fbbee 100755 --- a/benchmarks/launch_tgi_server.sh +++ b/benchmarks/launch_tgi_server.sh @@ -6,7 +6,7 @@ TOKENS=$2 docker run -e HF_TOKEN=$HF_TOKEN --gpus all --shm-size 1g -p $PORT:80 \ -v $PWD/data:/data \ - ghcr.io/huggingface/text-generation-inference:1.4.0 \ + ghcr.io/huggingface/text-generation-inference:2.2.0 \ --model-id $MODEL \ --sharded false \ --max-input-length 1024 \