Preparing for release. (#2285)

* Preparing for release.

* Updating docs.

* Fixing token within the docker image for the launcher.

docs/source/installation_amd.md

@@ -11,7 +11,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
     --device=/dev/kfd --device=/dev/dri --group-add video \
     --ipc=host --shm-size 256g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.1.1-rocm \
+    ghcr.io/huggingface/text-generation-inference:2.2.0-rocm \
     --model-id $model
 ```
 

docs/source/installation_intel.md

@@ -12,7 +12,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm --privileged --cap-add=sys_nice \
     --device=/dev/dri \
     --ipc=host --shm-size 1g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:latest-intel \
+    ghcr.io/huggingface/text-generation-inference:2.2.0-intel \
     --model-id $model --cuda-graphs 0
 ```
 

docs/source/installation_nvidia.md

@@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
 docker run --gpus all --shm-size 64g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.1.1 \
+    ghcr.io/huggingface/text-generation-inference:2.2.0 \
     --model-id $model
 ```
 

docs/source/quicktour.md

@@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
 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:2.1.1 \
+    ghcr.io/huggingface/text-generation-inference:2.2.0 \
     --model-id $model
 ```
 
@@ -88,7 +88,7 @@ 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:2.1.1 --help
+docker run ghcr.io/huggingface/text-generation-inference:2.2.0 --help
 ```
 
 </Tip>

launcher/src/main.rs

@@ -1,7 +1,10 @@
 /// Copyright (C) 2024 Habana Labs, Ltd. an Intel Company.
 
 use clap::{Parser, ValueEnum};
-use hf_hub::{api::sync::Api, Repo, RepoType};
+use hf_hub::{
+    api::sync::{Api, ApiBuilder},
+    Repo, RepoType,
+};
 use nix::sys::signal::{self, Signal};
 use nix::unistd::Pid;
 use serde::Deserialize;
@@ -1415,7 +1418,13 @@ fn main() -> Result<(), LauncherError> {
         let mut path = std::path::Path::new(&args.model_id).to_path_buf();
         let filename = if !path.exists() {
             // Assume it's a hub id
-            let api = Api::new()?;
+
+            let api = if let Ok(token) = std::env::var("HF_TOKEN") {
+                // env variable has precedence over on file token.
+                ApiBuilder::new().with_token(Some(token)).build()?
+            } else {
+                Api::new()?
+            };
             let repo = if let Some(ref revision) = args.revision {
                 api.repo(Repo::with_revision(
                     model_id,