Preparing patch release. (huggingface#2186)

yuanwu2017 · Sep 24, 2024 · 2e09ebe · 2e09ebe
1 parent 74ddd12
commit 2e09ebe
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 4 deletions.
diff --git a/docs/source/installation_amd.md b/docs/source/installation_amd.md
@@ -11,7 +11,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
     --device=/dev/kfd --device=/dev/dri --group-add video \
     --ipc=host --shm-size 256g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.1.0-rocm \
+    ghcr.io/huggingface/text-generation-inference:2.1.1-rocm \
     --model-id $model
 ```
 

diff --git a/docs/source/installation_nvidia.md b/docs/source/installation_nvidia.md
@@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
 docker run --gpus all --shm-size 64g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.1.0 \
+    ghcr.io/huggingface/text-generation-inference:2.1.1 \
     --model-id $model
 ```
 

diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md
@@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.1.0 \
+    ghcr.io/huggingface/text-generation-inference:2.1.1 \
     --model-id $model
 ```
 
@@ -88,7 +88,7 @@ curl 127.0.0.1:8080/generate \
 To see all possible deploy flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more.
 
 ```bash
-docker run ghcr.io/huggingface/text-generation-inference:2.1.0 --help
+docker run ghcr.io/huggingface/text-generation-inference:2.1.1 --help
 ```
 
 </Tip>