v0.7.0 (#353)

huggingface · May 23, 2023 · d31562f · d31562f
1 parent 9420053
commit d31562f
Show file tree

Hide file tree

Showing 5 changed files with 8 additions and 8 deletions.
diff --git a/Cargo.lock b/Cargo.lock
diff --git 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
@@ -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
@@ -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
@@ -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 <[email protected]>"]