v0.9.4 (#713)

huggingface · Jul 27, 2023 · 9f18f4c · 9f18f4c
1 parent ab96b9a
commit 9f18f4c
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 = "0.9.3"
+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
@@ -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
@@ -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
@@ -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>"]