diff --git a/Cargo.lock b/Cargo.lock index d64634a6..3cac30fb 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -4650,7 +4650,7 @@ dependencies = [ [[package]] name = "text-generation-backends-trtllm" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "async-trait", "clap 4.5.32", @@ -4671,7 +4671,7 @@ dependencies = [ [[package]] name = "text-generation-benchmark" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "average", "clap 4.5.32", @@ -4691,7 +4691,7 @@ dependencies = [ [[package]] name = "text-generation-client" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "async-trait", "base64 0.22.1", @@ -4709,7 +4709,7 @@ dependencies = [ [[package]] name = "text-generation-launcher" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "clap 4.5.32", "ctrlc", @@ -4730,7 +4730,7 @@ dependencies = [ [[package]] name = "text-generation-router" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "anyhow", "async-stream", @@ -4782,7 +4782,7 @@ dependencies = [ [[package]] name = "text-generation-router-llamacpp" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "async-trait", "bindgen 0.71.1", @@ -4800,7 +4800,7 @@ dependencies = [ [[package]] name = "text-generation-router-v2" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "async-stream", "async-trait", @@ -4849,7 +4849,7 @@ dependencies = [ [[package]] name = "text-generation-router-v3" -version = "3.2.2-dev0" +version = "3.2.3-dev0" dependencies = [ "async-stream", "async-trait", diff --git a/Cargo.toml b/Cargo.toml index 9b818837..1bc736ba 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -21,7 +21,7 @@ default-members = [ resolver = "2" [workspace.package] -version = "3.2.2-dev0" +version = "3.2.3-dev0" edition = "2021" authors = ["Olivier Dehaene"] homepage = "https://github.com/huggingface/text-generation-inference" diff --git a/README.md b/README.md index 23d87f9a..ed7b4809 100644 --- a/README.md +++ b/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:3.2.2 --model-id $model + ghcr.io/huggingface/text-generation-inference:3.2.3 --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/installation_amd#using-tgi-with-amd-gpus). 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:3.2.2-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/installation_amd#using-tgi-with-amd-gpus). 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:3.2.3-rocm --model-id $model` instead of the command above. To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli): ``` @@ -152,7 +152,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading token= docker run --gpus all --shm-size 1g -e HF_TOKEN=$token -p 8080:80 -v $volume:/data \ - ghcr.io/huggingface/text-generation-inference:3.2.2 --model-id $model + ghcr.io/huggingface/text-generation-inference:3.2.3 --model-id $model ``` ### A note on Shared Memory (shm) diff --git a/docs/openapi.json b/docs/openapi.json index 55fc7ec6..ad512479 100644 --- a/docs/openapi.json +++ b/docs/openapi.json @@ -10,7 +10,7 @@ "name": "Apache 2.0", "url": "https://www.apache.org/licenses/LICENSE-2.0" }, - "version": "3.2.2-dev0" + "version": "3.2.3-dev0" }, "paths": { "/": { diff --git a/docs/source/backends/gaudi.mdx b/docs/source/backends/gaudi.mdx index 6dcf973d..5c54d19d 100644 --- a/docs/source/backends/gaudi.mdx +++ b/docs/source/backends/gaudi.mdx @@ -20,7 +20,7 @@ hf_token=YOUR_HF_ACCESS_TOKEN docker run --runtime=habana --cap-add=sys_nice --ipc=host \ -p 8080:80 -v $volume:/data -e HF_TOKEN=$hf_token \ - ghcr.io/huggingface/text-generation-inference:3.2.2-gaudi \ + ghcr.io/huggingface/text-generation-inference:3.2.3-gaudi \ --model-id $model ``` @@ -52,7 +52,7 @@ hf_token=YOUR_ACCESS_TOKEN docker run --runtime=habana --cap-add=sys_nice --ipc=host \ -p 8080:80 -v $volume:/data -e HF_TOKEN=$hf_token \ - ghcr.io/huggingface/text-generation-inference:3.2.2-gaudi \ + ghcr.io/huggingface/text-generation-inference:3.2.3-gaudi \ --model-id $model ``` @@ -115,7 +115,7 @@ docker run -p 8080:80 \ -e BATCH_BUCKET_SIZE=256 \ -e PREFILL_BATCH_BUCKET_SIZE=4 \ -e PAD_SEQUENCE_TO_MULTIPLE_OF=64 \ - ghcr.io/huggingface/text-generation-inference:3.2.2-gaudi \ + ghcr.io/huggingface/text-generation-inference:3.2.3-gaudi \ --model-id $model \ --sharded true --num-shard 8 \ --max-input-tokens 1024 --max-total-tokens 2048 \ @@ -141,7 +141,7 @@ docker run -p 8080:80 \ -v $volume:/data \ -e PREFILL_BATCH_BUCKET_SIZE=1 \ -e BATCH_BUCKET_SIZE=1 \ - ghcr.io/huggingface/text-generation-inference:3.2.2-gaudi \ + ghcr.io/huggingface/text-generation-inference:3.2.3-gaudi \ --model-id $model \ --max-input-tokens 4096 --max-batch-prefill-tokens 16384 \ --max-total-tokens 8192 --max-batch-size 4 @@ -208,7 +208,7 @@ docker run --runtime=habana --ipc=host --cap-add=sys_nice \ -e PROF_PATH=/tmp/hpu_profile \ -e PROF_RANKS=0 \ -e PROF_RECORD_SHAPES=True \ - ghcr.io/huggingface/text-generation-inference:3.2.2-gaudi \ + ghcr.io/huggingface/text-generation-inference:3.2.3-gaudi \ --model-id $model ``` diff --git a/docs/source/backends/neuron.md b/docs/source/backends/neuron.md index e528197f..c8e3876e 100644 --- a/docs/source/backends/neuron.md +++ b/docs/source/backends/neuron.md @@ -31,7 +31,7 @@ deployment instructions in the model card: The service is launched simply by running the text-generation-inference container with two sets of parameters: ``` -docker run ghcr.io/huggingface/text-generation-inference:3.2.2-neuron +docker run ghcr.io/huggingface/text-generation-inference:3.2.3-neuron ``` - system parameters are used to map ports, volumes and devices between the host and the service, diff --git a/docs/source/basic_tutorials/gated_model_access.md b/docs/source/basic_tutorials/gated_model_access.md index 48d3abfe..a45190f7 100644 --- a/docs/source/basic_tutorials/gated_model_access.md +++ b/docs/source/basic_tutorials/gated_model_access.md @@ -19,6 +19,6 @@ docker run --gpus all \ --shm-size 1g \ -e HF_TOKEN=$token \ -p 8080:80 \ - -v $volume:/data ghcr.io/huggingface/text-generation-inference:3.2.2 \ + -v $volume:/data ghcr.io/huggingface/text-generation-inference:3.2.3 \ --model-id $model ``` diff --git a/docs/source/conceptual/quantization.md b/docs/source/conceptual/quantization.md index 4790578d..3aa7bb95 100644 --- a/docs/source/conceptual/quantization.md +++ b/docs/source/conceptual/quantization.md @@ -19,7 +19,7 @@ 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:3.2.2 --model-id $model --quantize bitsandbytes +docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:3.2.3 --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. @@ -27,7 +27,7 @@ docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingf 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:3.2.2 --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:3.2.3 --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:3.2.2 --model-id $model --quantize gptq +docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:3.2.3 --model-id $model --quantize gptq ``` Note that TGI's GPTQ implementation doesn't use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) under the hood. However, models quantized using AutoGPTQ or Optimum can still be served by TGI. diff --git a/docs/source/installation_amd.md b/docs/source/installation_amd.md index bd2f9148..cec52acb 100644 --- a/docs/source/installation_amd.md +++ b/docs/source/installation_amd.md @@ -11,7 +11,7 @@ volume=$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:3.2.2-rocm \ + ghcr.io/huggingface/text-generation-inference:3.2.3-rocm \ --model-id $model ``` diff --git a/docs/source/installation_intel.md b/docs/source/installation_intel.md index 60d2f896..12fdd9f5 100644 --- a/docs/source/installation_intel.md +++ b/docs/source/installation_intel.md @@ -12,7 +12,7 @@ volume=$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:3.2.2-intel-xpu \ + ghcr.io/huggingface/text-generation-inference:3.2.3-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:3.2.2-intel-cpu \ + ghcr.io/huggingface/text-generation-inference:3.2.3-intel-cpu \ --model-id $model --cuda-graphs 0 ``` diff --git a/docs/source/installation_nvidia.md b/docs/source/installation_nvidia.md index 0ed0da32..0c3a0bd9 100644 --- a/docs/source/installation_nvidia.md +++ b/docs/source/installation_nvidia.md @@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B volume=$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:3.2.2 \ + ghcr.io/huggingface/text-generation-inference:3.2.3 \ --model-id $model ``` diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md index 2ce9e686..e7f60e52 100644 --- a/docs/source/quicktour.md +++ b/docs/source/quicktour.md @@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B volume=$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:3.2.2 \ + ghcr.io/huggingface/text-generation-inference:3.2.3 \ --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:3.2.2 --help +docker run ghcr.io/huggingface/text-generation-inference:3.2.3 --help ``` diff --git a/docs/source/reference/api_reference.md b/docs/source/reference/api_reference.md index 7dc6768e..8e04b2a8 100644 --- a/docs/source/reference/api_reference.md +++ b/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="3.2.2"), + image_uri=get_huggingface_llm_image_uri("huggingface",version="3.2.3"), env=hub, role=role, )