Update README.md

README.md

@@ -40,7 +40,7 @@ _Note: For all samples, your environment must have access to cuda_
 #### Setup
 
 ```bash
-docker pull quay.io/wxpe/text-gen-server:speculative-decoding.ecd73c4
+docker pull quay.io/wxpe/text-gen-server:main.ee927a4
 docker run -d --rm --gpus all \
     --name my-tgis-server \
     -p 8033:8033 \
@@ -50,7 +50,7 @@ docker run -d --rm --gpus all \
     -e FLASH_ATTENTION=true \
     -e PAGED_ATTENTION=true \
     -e DTYPE_STR=float16 \
-    quay.io/wxpe/text-gen-server:speculative-decoding.ecd73c4
+    quay.io/wxpe/text-gen-server:main.ee927a4
 
 # check logs and wait for "gRPC server started on port 8033" and "HTTP server started on port 3000"
 docker logs my-tgis-server -f
@@ -58,7 +58,7 @@ docker logs my-tgis-server -f
 # get the client sample (Note: The first prompt will take longer as there is a warmup time)
 conda create -n tgis-client-env python=3.11
 conda activate tgis-client-env
-git clone --branch speculative-decoding --single-branch https://github.com/tdoublep/text-generation-inference.git
+git clone --branch main --single-branch https://github.com/IBM/text-generation-inference.git
 cd text-generation-inference/integration_tests
 make gen-client
 pip install . --no-cache-dir