Version 1.0.1

Cargo.lock

@@ -2893,7 +2893,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "1.0.0"
+version = "1.0.1"
 dependencies = [
  "average",
  "clap",
@@ -2913,7 +2913,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "1.0.0"
+version = "1.0.1"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2929,7 +2929,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "1.0.0"
+version = "1.0.1"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2945,7 +2945,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "1.0.0"
+version = "1.0.1"
 dependencies = [
  "async-stream",
  "axum",

Cargo.toml

@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.0.0"
+version = "1.0.1"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

README.md

@@ -83,7 +83,7 @@ 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:1.0.0 --model-id $model
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --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.
 
@@ -150,7 +150,7 @@ 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:1.0.0 --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:1.0.1 --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": "1.0.0"
+    "version": "1.0.1"
   },
   "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:1.0.0 \
+    -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 \
     --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:1.0.0 --model-id $model
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model
 ```
 
 <Tip warning={true}>

server/flash-attention

@@ -0,0 +1 @@
+Subproject commit 3a9bfd076f98746c73362328958dbc68d145fbec

server/flash-attention-v2

@@ -0,0 +1 @@
+Subproject commit 4f285b354796fb17df8636485b9a04df3ebbb7dc

server/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "1.0.0"
+version = "1.0.1"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]
 

server/vllm

@@ -0,0 +1 @@
+Subproject commit d284b831c17f42a8ea63369a06138325f73c4cf9