chore: prepare 2.4.1 release (#2773)

* chore: prepare 2.4.1 release

* fix tests

* fmt

Cargo.toml

@@ -20,7 +20,7 @@ default-members = [
 resolver = "2"
 
 [workspace.package]
-version = "2.4.1-dev0"
+version = "2.4.2-dev0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

README.md

@@ -84,7 +84,7 @@ model=HuggingFaceH4/zephyr-7b-beta
 volume=$PWD/data
 
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model
+    ghcr.io/huggingface/text-generation-inference:2.4.1 --model-id $model
 ```
 
 And then you can make requests like
@@ -121,7 +121,7 @@ curl localhost:8080/v1/chat/completions \
 
 **Note:** To use NVIDIA 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 12.2 or higher. For running the Docker container on a machine with no GPUs or CUDA support, it is enough to remove the `--gpus all` flag and add `--disable-custom-kernels`, please note CPU is not the intended platform for this project, so performance might be subpar.
 
-**Note:** TGI supports AMD Instinct MI210 and MI250 GPUs. Details can be found in the [Supported Hardware documentation](https://huggingface.co/docs/text-generation-inference/supported_models#supported-hardware). To use AMD GPUs, please use `docker run --device /dev/kfd --device /dev/dri --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0-rocm --model-id $model` instead of the command above.
+**Note:** TGI supports AMD Instinct MI210 and MI250 GPUs. Details can be found in the [Supported Hardware documentation](https://huggingface.co/docs/text-generation-inference/supported_models#supported-hardware). To use AMD GPUs, please use `docker run --device /dev/kfd --device /dev/dri --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.1-rocm --model-id $model` instead of the command above.
 
 To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli):
 ```
@@ -151,7 +151,7 @@ model=meta-llama/Meta-Llama-3.1-8B-Instruct
 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 HF_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model
+docker run --gpus all --shm-size 1g -e HF_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.1 --model-id $model
 ```
 
 ### A note on Shared Memory (shm)

benchmark/src/main.rs

@@ -147,15 +147,15 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
             tracing::info!("Downloading tokenizer");
 
             // Parse Huggingface hub token
-            let auth_token = std::env::var("HF_TOKEN")
+            let token = std::env::var("HF_TOKEN")
                 .or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN"))
                 .ok();
 
             // Download and instantiate tokenizer
             // We need to download it outside of the Tokio runtime
             let params = FromPretrainedParameters {
                 revision,
-                auth_token,
+                token,
                 ..Default::default()
             };
             Tokenizer::from_pretrained(tokenizer_name.clone(), Some(params)).unwrap()

docs/openapi.json

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "2.4.1-dev0"
+    "version": "2.4.2-dev0"
   },
   "paths": {
     "/": {

docs/source/basic_tutorials/gated_model_access.md

@@ -19,6 +19,6 @@ docker run --gpus all \
     --shm-size 1g \
     -e HF_TOKEN=$token \
     -p 8080:80 \
-    -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0 \
+    -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.1 \
     --model-id $model
 ```

docs/source/conceptual/quantization.md

@@ -19,15 +19,15 @@ bitsandbytes is a library used to apply 8-bit and 4-bit quantization to models.
 In TGI, you can use 8-bit quantization by adding `--quantize bitsandbytes` like below 👇
 
 ```bash
-docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model --quantize bitsandbytes
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.1 --model-id $model --quantize bitsandbytes
 ```
 
 4-bit quantization is also possible with bitsandbytes. You can choose one of the following 4-bit data types: 4-bit float (`fp4`), or 4-bit `NormalFloat` (`nf4`). These data types were introduced in the context of parameter-efficient fine-tuning, but you can apply them for inference by automatically converting the model weights on load.
 
 In TGI, you can use 4-bit quantization by adding `--quantize bitsandbytes-nf4` or `--quantize bitsandbytes-fp4` like below 👇
 
 ```bash
-docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model --quantize bitsandbytes-nf4
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.1 --model-id $model --quantize bitsandbytes-nf4
 ```
 
 You can get more information about 8-bit quantization by reading this [blog post](https://huggingface.co/blog/hf-bitsandbytes-integration), and 4-bit quantization by reading [this blog post](https://huggingface.co/blog/4bit-transformers-bitsandbytes).
@@ -48,7 +48,7 @@ $$({\hat{W}_{l}}^{*} = argmin_{\hat{W_{l}}} ||W_{l}X-\hat{W}_{l}X||^{2}_{2})$$
 TGI allows you to both run an already GPTQ quantized model (see available models [here](https://huggingface.co/models?search=gptq)) or quantize a model of your choice using quantization script. You can run a quantized model by simply passing --quantize like below 👇
 
 ```bash
-docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model --quantize gptq
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.1 --model-id $model --quantize gptq
 ```
 
 Note that TGI's GPTQ implementation doesn't use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) under the hood. However, models quantized using AutoGPTQ or Optimum can still be served by TGI.

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:2.4.0-rocm \
+    ghcr.io/huggingface/text-generation-inference:2.4.1-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:2.4.0-intel-xpu \
+    ghcr.io/huggingface/text-generation-inference:2.4.1-intel-xpu \
     --model-id $model --cuda-graphs 0
 ```
 
@@ -29,7 +29,7 @@ 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:2.4.0-intel-cpu \
+    ghcr.io/huggingface/text-generation-inference:2.4.1-intel-cpu \
     --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:2.4.0 \
+    ghcr.io/huggingface/text-generation-inference:2.4.1 \
     --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:2.4.0 \
+    ghcr.io/huggingface/text-generation-inference:2.4.1 \
     --model-id $model
 ```
 
@@ -96,7 +96,7 @@ 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:2.4.0 --help
+docker run ghcr.io/huggingface/text-generation-inference:2.4.1 --help
 ```
 
 </Tip>

docs/source/reference/api_reference.md

@@ -163,7 +163,7 @@ hub = {
 
 # create Hugging Face Model Class
 huggingface_model = HuggingFaceModel(
- image_uri=get_huggingface_llm_image_uri("huggingface",version="2.4.0"),
+ image_uri=get_huggingface_llm_image_uri("huggingface",version="2.4.1"),
  env=hub,
  role=role,
 )

integration-tests/models/__snapshots__/test_flash_qwen2_vl/test_flash_qwen2_vl_simple.json

@@ -17,7 +17,7 @@
   "id": "",
   "model": "Qwen/Qwen2-VL-7B-Instruct",
   "object": "chat.completion",
-  "system_fingerprint": "2.4.1-dev0-native",
+  "system_fingerprint": "2.4.2-dev0-native",
   "usage": {
     "completion_tokens": 58,
     "prompt_tokens": 349,

integration-tests/models/__snapshots__/test_flash_qwen2_vl/test_flash_qwen2_vl_simple_streaming.json

@@ -15,6 +15,6 @@
   "id": "",
   "model": "Qwen/Qwen2-VL-7B-Instruct",
   "object": "chat.completion.chunk",
-  "system_fingerprint": "2.4.1-dev0-native",
+  "system_fingerprint": "2.4.2-dev0-native",
   "usage": null
 }

integration-tests/models/__snapshots__/test_mllama/test_mllama_load.json

@@ -18,7 +18,7 @@
     "id": "",
     "model": "meta-llama/Llama-3.2-11B-Vision-Instruct",
     "object": "chat.completion",
-    "system_fingerprint": "2.4.1-dev0-native",
+    "system_fingerprint": "2.4.2-dev0-native",
     "usage": {
       "completion_tokens": 10,
       "prompt_tokens": 50,
@@ -44,7 +44,7 @@
     "id": "",
     "model": "meta-llama/Llama-3.2-11B-Vision-Instruct",
     "object": "chat.completion",
-    "system_fingerprint": "2.4.1-dev0-native",
+    "system_fingerprint": "2.4.2-dev0-native",
     "usage": {
       "completion_tokens": 10,
       "prompt_tokens": 50,
@@ -70,7 +70,7 @@
     "id": "",
     "model": "meta-llama/Llama-3.2-11B-Vision-Instruct",
     "object": "chat.completion",
-    "system_fingerprint": "2.4.1-dev0-native",
+    "system_fingerprint": "2.4.2-dev0-native",
     "usage": {
       "completion_tokens": 10,
       "prompt_tokens": 50,
@@ -96,7 +96,7 @@
     "id": "",
     "model": "meta-llama/Llama-3.2-11B-Vision-Instruct",
     "object": "chat.completion",
-    "system_fingerprint": "2.4.1-dev0-native",
+    "system_fingerprint": "2.4.2-dev0-native",
     "usage": {
       "completion_tokens": 10,
       "prompt_tokens": 50,

integration-tests/models/__snapshots__/test_mllama/test_mllama_simpl.json

@@ -17,7 +17,7 @@
   "id": "",
   "model": "meta-llama/Llama-3.2-11B-Vision-Instruct",
   "object": "chat.completion",
-  "system_fingerprint": "2.4.1-dev0-native",
+  "system_fingerprint": "2.4.2-dev0-native",
   "usage": {
     "completion_tokens": 10,
     "prompt_tokens": 50,

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_insufficient_information.json

@@ -17,7 +17,7 @@
   "id": "",
   "model": "meta-llama/Llama-3.1-8B-Instruct",
   "object": "chat.completion",
-  "system_fingerprint": "2.4.1-dev0-native",
+  "system_fingerprint": "2.4.2-dev0-native",
   "usage": {
     "completion_tokens": 23,
     "prompt_tokens": 604,

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_insufficient_information_stream.json

@@ -15,6 +15,6 @@
   "id": "",
   "model": "meta-llama/Llama-3.1-8B-Instruct",
   "object": "chat.completion.chunk",
-  "system_fingerprint": "2.4.1-dev0-native",
+  "system_fingerprint": "2.4.2-dev0-native",
   "usage": null
 }

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_sea_creatures_stream.json

@@ -15,6 +15,6 @@
   "id": "",
   "model": "meta-llama/Llama-3.1-8B-Instruct",
   "object": "chat.completion.chunk",
-  "system_fingerprint": "2.4.1-dev0-native",
+  "system_fingerprint": "2.4.2-dev0-native",
   "usage": null
 }