v1.0.0

Cargo.lock

@@ -2893,7 +2893,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.9.4"
+version = "1.0.0"
 dependencies = [
  "average",
  "clap",
@@ -2913,7 +2913,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.9.4"
+version = "1.0.0"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2929,7 +2929,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.9.4"
+version = "1.0.0"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2945,7 +2945,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.9.4"
+version = "1.0.0"
 dependencies = [
  "async-stream",
  "axum",

Cargo.toml

@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.9.4"
+version = "1.0.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

README.md

@@ -7,16 +7,18 @@
 <a href="https://github.com/huggingface/text-generation-inference">
   <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/huggingface/text-generation-inference?style=social">
 </a>
-<a href="https://github.com/huggingface/text-generation-inference/blob/main/LICENSE">
-  <img alt="License" src="https://img.shields.io/github/license/huggingface/text-generation-inference">
-</a>
 <a href="https://huggingface.github.io/text-generation-inference">
   <img alt="Swagger API documentation" src="https://img.shields.io/badge/API-Swagger-informational">
 </a>
-</div>
+
 
 A Rust, Python and gRPC server for text generation inference. Used in production at [HuggingFace](https://huggingface.co)
-to power LLMs api-inference widgets.
+to power Hugging Chat, the Inference API and Inference Endpoint.
+
+Text Generation Inference v1.0 was released under a new license: HFOIL 1.0.
+Learn more about the rationale behind the change [here](https://github.com/huggingface/text-generation-inference/issues/726).
+
+</div>
 
 ## Table of contents
 
@@ -85,7 +87,7 @@ 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:0.9.4 --model-id $model
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --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.
 
@@ -152,7 +154,7 @@ model=meta-llama/Llama-2-7b-chat-hf
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 token=<your cli READ token>
 
-docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.9.3 --model-id $model
+docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model
 ```
 
 ### A note on Shared Memory (shm)

docs/openapi.json

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "0.9.4"
+    "version": "1.0.0"
   },
   "paths": {
     "/": {

server/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.9.4"
+version = "1.0.0"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]