v1.3.0

Cargo.lock

@@ -2798,7 +2798,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "1.2.0"
+version = "1.3.0"
 dependencies = [
  "average",
  "clap",
@@ -2819,7 +2819,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "1.2.0"
+version = "1.3.0"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2836,7 +2836,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "1.2.0"
+version = "1.3.0"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2852,7 +2852,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "1.2.0"
+version = "1.3.0"
 dependencies = [
  "async-stream",
  "axum",

Cargo.toml

@@ -9,7 +9,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "1.2.0"
+version = "1.3.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

docs/openapi.json

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "1.2.0"
+    "version": "1.3.0"
   },
   "paths": {
     "/": {

docs/source/basic_tutorials/gated_model_access.md

@@ -19,6 +19,6 @@ 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:1.2 \
+    -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 \
     --model-id $model
 ```

docs/source/quicktour.md

@@ -8,7 +8,7 @@ Let's say you want to deploy [Falcon-7B Instruct](https://huggingface.co/tiiuae/
 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:1.2 --model-id $model
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model
 ```
 
 <Tip warning={true}>
@@ -20,7 +20,7 @@ To use NVIDIA GPUs, you need to install the [NVIDIA Container Toolkit](https://d
 TGI also supports ROCm-enabled AMD GPUs (only MI210 and MI250 are tested), details are available in the [Supported Hardware section](./supported_models#supported-hardware) and [AMD documentation](https://rocm.docs.amd.com/en/latest/deploy/docker.html). To launch TGI on ROCm GPUs, please use instead:
 
 ```bash
-docker run --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.2-rocm --model-id $model
+docker run --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3-rocm --model-id $model
 ```
 
 Once TGI is running, you can use the `generate` endpoint by doing requests. To learn more about how to query the endpoints, check the [Consuming TGI](./basic_tutorials/consuming_tgi) section, where we show examples with utility libraries and UIs. Below you can see a simple snippet to query the endpoint.
@@ -91,7 +91,7 @@ curl 127.0.0.1:8080/generate \
 To see all possible deploy flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more.
 
 ```bash
-docker run ghcr.io/huggingface/text-generation-inference:1.2 --help
+docker run ghcr.io/huggingface/text-generation-inference:1.3 --help
 ```
 
 </Tip>

integration-tests/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-integration-tests"
-version = "1.2.0"
+version = "1.3.0"
 description = "Text Generation Inference integration tests"
 authors = ["Nicolas Patry <nicolas@huggingface.co>"]
 

server/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "1.2.0"
+version = "1.3.0"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]