From 9f18f4c00627e1a0ad696b6774e5ad7ca8f4261c Mon Sep 17 00:00:00 2001
From: OlivierDehaene <olivier@huggingface.co>
Date: Thu, 27 Jul 2023 19:25:15 +0200
Subject: [PATCH] v0.9.4 (#713)

---
 Cargo.lock            | 8 ++++----
 Cargo.toml            | 2 +-
 README.md             | 2 +-
 docs/openapi.json     | 2 +-
 server/pyproject.toml | 2 +-
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 539cf124..8984ea6a 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2893,7 +2893,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.9.3"
+version = "0.9.4"
 dependencies = [
  "average",
  "clap",
@@ -2913,7 +2913,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.9.3"
+version = "0.9.4"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2929,7 +2929,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.9.3"
+version = "0.9.4"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2945,7 +2945,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.9.3"
+version = "0.9.4"
 dependencies = [
  "async-stream",
  "axum",
diff --git a/Cargo.toml b/Cargo.toml
index 49b7717a..3bfe9831 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.9.3"
+version = "0.9.4"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/README.md b/README.md
index 9e256c9d..effab42e 100644
--- a/README.md
+++ b/README.md
@@ -84,7 +84,7 @@ The easiest way of getting started is using the official Docker container:
 model=tiiuae/falcon-7b-instruct
 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:0.9.3 --model-id $model
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.9.4 --model-id $model
 ```
 **Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.
 
diff --git a/docs/openapi.json b/docs/openapi.json
index 80240460..9a672382 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": "0.9.3"
+    "version": "0.9.4"
   },
   "paths": {
     "/": {
diff --git a/server/pyproject.toml b/server/pyproject.toml
index 40cd31ee..3ee3351c 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.9.3"
+version = "0.9.4"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]