From d31562f300ee8cd44b3ead667a9f260d6a762f7a Mon Sep 17 00:00:00 2001
From: OlivierDehaene <olivier@huggingface.co>
Date: Tue, 23 May 2023 21:20:49 +0200
Subject: [PATCH] v0.7.0 (#353)

---
 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 48595077fe5..1dcc7c97687 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2516,7 +2516,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "average",
  "clap",
@@ -2535,7 +2535,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2551,7 +2551,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2567,7 +2567,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "async-stream",
  "axum",
diff --git a/Cargo.toml b/Cargo.toml
index d34b10bfd59..4ed0524e8de 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.7.0-dev"
+version = "0.7.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/README.md b/README.md
index 918ea5e2ba2..30e085b253a 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,7 @@ model=bigscience/bloom-560m
 num_shard=2
 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:latest --model-id $model --num-shard $num_shard
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.7 --model-id $model --num-shard $num_shard
 ```
 **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 fbac7786f8c..5bccc9fc3a4 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": "0.7.0-dev"
+    "version": "0.7.0"
   },
   "paths": {
     "/": {
diff --git a/server/pyproject.toml b/server/pyproject.toml
index 932a094c41e..d674172d83e 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.6.0"
+version = "0.7.0"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]