Update benchmark scripts (#8)

benchmark/dspy/README.md

@@ -23,7 +23,7 @@ python3 bench_dspy_intro.py --backend sglang
 ```
 docker run --name tgi --rm -ti --gpus all --network host \
   -v /home/ubuntu/model_weights/Llama-2-7b-chat-hf:/Llama-2-7b-chat-hf \
-  ghcr.io/huggingface/text-generation-inference:1.1.0 \
+  ghcr.io/huggingface/text-generation-inference:1.3.0 \
   --model-id /Llama-2-7b-chat-hf --num-shard 1  --trust-remote-code \
   --max-input-length 2048 --max-total-tokens 4096 \
   --port 24000