parent
d22b0c1fbe
commit
f6e2f05b16
|
@ -20,7 +20,7 @@ default-members = [
|
|||
resolver = "2"
|
||||
|
||||
[workspace.package]
|
||||
version = "2.3.1-dev0"
|
||||
version = "2.3.2-dev0"
|
||||
edition = "2021"
|
||||
authors = ["Olivier Dehaene"]
|
||||
homepage = "https://github.com/huggingface/text-generation-inference"
|
||||
|
|
|
@ -83,7 +83,7 @@ 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:2.3.0 --model-id $model
|
||||
ghcr.io/huggingface/text-generation-inference:2.3.1 --model-id $model
|
||||
```
|
||||
|
||||
And then you can make requests like
|
||||
|
|
|
@ -10,7 +10,7 @@
|
|||
"name": "Apache 2.0",
|
||||
"url": "https://www.apache.org/licenses/LICENSE-2.0"
|
||||
},
|
||||
"version": "2.3.1-dev0"
|
||||
"version": "2.3.2-dev0"
|
||||
},
|
||||
"paths": {
|
||||
"/": {
|
||||
|
|
|
@ -11,7 +11,7 @@ volume=$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:2.3.0-rocm \
|
||||
ghcr.io/huggingface/text-generation-inference:2.3.1-rocm \
|
||||
--model-id $model
|
||||
```
|
||||
|
||||
|
|
|
@ -12,7 +12,7 @@ volume=$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:2.3.0-intel-xpu \
|
||||
ghcr.io/huggingface/text-generation-inference:2.3.1-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:2.3.0-intel-cpu \
|
||||
ghcr.io/huggingface/text-generation-inference:2.3.1-intel-cpu \
|
||||
--model-id $model --cuda-graphs 0
|
||||
```
|
||||
|
||||
|
|
|
@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
|
|||
volume=$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:2.3.0 \
|
||||
ghcr.io/huggingface/text-generation-inference:2.3.1 \
|
||||
--model-id $model
|
||||
```
|
||||
|
||||
|
|
|
@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
|
|||
volume=$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:2.3.0 \
|
||||
ghcr.io/huggingface/text-generation-inference:2.3.1 \
|
||||
--model-id $model
|
||||
```
|
||||
|
||||
|
|
Loading…
Reference in New Issue