v1.2.0
This commit is contained in:
parent
624800c4de
commit
ccd5725a0c
File diff suppressed because it is too large
Load Diff
|
@ -8,7 +8,7 @@ members = [
|
|||
]
|
||||
|
||||
[workspace.package]
|
||||
version = "1.1.1"
|
||||
version = "1.2.0"
|
||||
edition = "2021"
|
||||
authors = ["Olivier Dehaene"]
|
||||
homepage = "https://github.com/huggingface/text-generation-inference"
|
||||
|
|
|
@ -62,7 +62,7 @@ For a detailed starting guide, please see the [Quick Tour](https://huggingface.c
|
|||
model=HuggingFaceH4/zephyr-7b-beta
|
||||
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:1.1.1 --model-id $model
|
||||
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.2 --model-id $model
|
||||
```
|
||||
|
||||
And then you can make requests like
|
||||
|
@ -76,7 +76,7 @@ curl 127.0.0.1:8080/generate \
|
|||
|
||||
**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 11.8 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 [to some extent](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:1.1.0+rocm --model-id $model` instead of the command above.
|
||||
**Note:** TGI supports AMD Instinct MI210 and MI250 [to some extent](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:1.2+rocm --model-id $model` instead of the command above.
|
||||
|
||||
To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli):
|
||||
```
|
||||
|
@ -106,7 +106,7 @@ model=meta-llama/Llama-2-7b-chat-hf
|
|||
volume=$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:1.1.1 --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:1.2 --model-id $model
|
||||
```
|
||||
|
||||
### A note on Shared Memory (shm)
|
||||
|
|
|
@ -10,7 +10,7 @@
|
|||
"name": "Apache 2.0",
|
||||
"url": "https://www.apache.org/licenses/LICENSE-2.0"
|
||||
},
|
||||
"version": "1.1.1"
|
||||
"version": "1.2.0"
|
||||
},
|
||||
"paths": {
|
||||
"/": {
|
||||
|
|
|
@ -19,6 +19,6 @@ docker run --gpus all \
|
|||
--shm-size 1g \
|
||||
-e HUGGING_FACE_HUB_TOKEN=$token \
|
||||
-p 8080:80 \
|
||||
-v $volume:/data ghcr.io/huggingface/text-generation-inference:1.1.1 \
|
||||
-v $volume:/data ghcr.io/huggingface/text-generation-inference:1.2 \
|
||||
--model-id $model
|
||||
```
|
||||
|
|
|
@ -8,14 +8,14 @@ Let's say you want to deploy [Falcon-7B Instruct](https://huggingface.co/tiiuae/
|
|||
model=tiiuae/falcon-7b-instruct
|
||||
volume=$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:1.1.1 --model-id $model
|
||||
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.2 --model-id $model
|
||||
```
|
||||
|
||||
<Tip warning={true}>
|
||||
|
||||
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.
|
||||
|
||||
To use TGI on RoCm-enabled AMD GPUs (only MI210 and MI250 are tested), please use the image `ghcr.io/huggingface/text-generation-inference:1.1.1+rocm` instead. For details about the usage on RoCm, please refer to the [Supported Hardware section](./supported_models#supported-hardware) and [AMD documentation](https://rocm.docs.amd.com/en/latest/deploy/docker.html).
|
||||
To use TGI on RoCm-enabled AMD GPUs (only MI210 and MI250 are tested), please use the image `ghcr.io/huggingface/text-generation-inference:1.2+rocm` instead. For details about the usage on RoCm, please refer to the [Supported Hardware section](./supported_models#supported-hardware) and [AMD documentation](https://rocm.docs.amd.com/en/latest/deploy/docker.html).
|
||||
|
||||
</Tip>
|
||||
|
||||
|
@ -87,7 +87,7 @@ 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:1.1.1 --help
|
||||
docker run ghcr.io/huggingface/text-generation-inference:1.2 --help
|
||||
```
|
||||
|
||||
</Tip>
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "text-generation-integration-tests"
|
||||
version = "1.1.1"
|
||||
version = "1.2.0"
|
||||
description = "Text Generation Inference integration tests"
|
||||
authors = ["Nicolas Patry <nicolas@huggingface.co>"]
|
||||
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "text-generation-server"
|
||||
version = "1.1.1"
|
||||
version = "1.2.0"
|
||||
description = "Text Generation Inference Python gRPC Server"
|
||||
authors = ["Olivier Dehaene <olivier@huggingface.co>"]
|
||||
|
||||
|
|
Loading…
Reference in New Issue