From f6e2f05b16c1d13f0e017450cad975244099de80 Mon Sep 17 00:00:00 2001
From: Nicolas Patry <patry.nicolas@protonmail.com>
Date: Thu, 3 Oct 2024 14:43:49 +0200
Subject: [PATCH] New release 2.3.1 (#2604)

* New release 2.3.1

* Update doc number
---
 Cargo.toml                         | 2 +-
 README.md                          | 2 +-
 docs/openapi.json                  | 2 +-
 docs/source/installation_amd.md    | 2 +-
 docs/source/installation_intel.md  | 4 ++--
 docs/source/installation_nvidia.md | 2 +-
 docs/source/quicktour.md           | 2 +-
 7 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index a783fadb099..ad2caeb8e63 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -20,7 +20,7 @@ default-members = [
 resolver = "2"
 
 [workspace.package]
-version = "2.3.1-dev0"
+version = "2.3.2-dev0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/README.md b/README.md
index 156fa5ccf60..df6912bf76c 100644
--- a/README.md
+++ b/README.md
@@ -83,7 +83,7 @@ model=HuggingFaceH4/zephyr-7b-beta
 volume=$PWD/data
 
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.3.0 --model-id $model
+    ghcr.io/huggingface/text-generation-inference:2.3.1 --model-id $model
 ```
 
 And then you can make requests like
diff --git a/docs/openapi.json b/docs/openapi.json
index 0b5b3ae37a6..67394a14f81 100644
--- a/docs/openapi.json
+++ b/docs/openapi.json
@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "2.3.1-dev0"
+    "version": "2.3.2-dev0"
   },
   "paths": {
     "/": {
diff --git a/docs/source/installation_amd.md b/docs/source/installation_amd.md
index 6806bac93e8..86d092eb421 100644
--- 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:2.3.0-rocm \
+    ghcr.io/huggingface/text-generation-inference:2.3.1-rocm \
     --model-id $model
 ```
 
diff --git a/docs/source/installation_intel.md b/docs/source/installation_intel.md
index fcbe550fb60..1435b331f3c 100644
--- a/docs/source/installation_intel.md
+++ b/docs/source/installation_intel.md
@@ -12,7 +12,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm --privileged --cap-add=sys_nice \
     --device=/dev/dri \
     --ipc=host --shm-size 1g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.3.0-intel-xpu \
+    ghcr.io/huggingface/text-generation-inference:2.3.1-intel-xpu \
     --model-id $model --cuda-graphs 0
 ```
 
@@ -29,7 +29,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm --privileged --cap-add=sys_nice \
     --device=/dev/dri \
     --ipc=host --shm-size 1g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.3.0-intel-cpu \
+    ghcr.io/huggingface/text-generation-inference:2.3.1-intel-cpu \
     --model-id $model --cuda-graphs 0
 ```
 
diff --git a/docs/source/installation_nvidia.md b/docs/source/installation_nvidia.md
index 8aa7a85a97c..634380fc235 100644
--- 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:2.3.0 \
+    ghcr.io/huggingface/text-generation-inference:2.3.1 \
     --model-id $model
 ```
 
diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md
index 338329649b8..655e6f9e98e 100644
--- 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:2.3.0 \
+    ghcr.io/huggingface/text-generation-inference:2.3.1 \
     --model-id $model
 ```