Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

New release 2.3.1 (#2604) 

* New release 2.3.1

* Update doc number
This commit is contained in:
Nicolas Patry 2024-10-03 14:43:49 +02:00 committed by GitHub
parent d22b0c1fbe
commit f6e2f05b16
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
7 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Cargo.toml
View File

@ -20,7 +20,7 @@ default-members = [
resolver = "2" resolver = "2"
[workspace.package] [workspace.package]
version = "2.3.1-dev0" version = "2.3.2-dev0"
edition = "2021" edition = "2021"
authors = ["Olivier Dehaene"] authors = ["Olivier Dehaene"]
homepage = "https://github.com/huggingface/text-generation-inference" homepage = "https://github.com/huggingface/text-generation-inference"

2
README.md
View File

@ -83,7 +83,7 @@ model=HuggingFaceH4/zephyr-7b-beta
volume=$PWD/data volume=$PWD/data
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/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 And then you can make requests like

2
docs/openapi.json
View File

@ -10,7 +10,7 @@
"name": "Apache 2.0", "name": "Apache 2.0",
"url": "https://www.apache.org/licenses/LICENSE-2.0" "url": "https://www.apache.org/licenses/LICENSE-2.0"
}, },
"version": "2.3.1-dev0" "version": "2.3.2-dev0"
}, },
"paths": { "paths": {
"/": { "/": {

2
docs/source/installation_amd.md
View File

@ -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 \ docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
--device=/dev/kfd --device=/dev/dri --group-add video \ --device=/dev/kfd --device=/dev/dri --group-add video \
--ipc=host --shm-size 256g --net host -v $volume:/data \ --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 --model-id $model
``` ```

4
docs/source/installation_intel.md
View File

@ -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 \ docker run --rm --privileged --cap-add=sys_nice \
--device=/dev/dri \ --device=/dev/dri \
--ipc=host --shm-size 1g --net host -v $volume:/data \ --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 --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 \ docker run --rm --privileged --cap-add=sys_nice \
--device=/dev/dri \ --device=/dev/dri \
--ipc=host --shm-size 1g --net host -v $volume:/data \ --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 --model-id $model --cuda-graphs 0
``` ```

2
docs/source/installation_nvidia.md
View File

@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run volume=$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 \ 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 --model-id $model
``` ```

2
docs/source/quicktour.md
View File

@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run volume=$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 \ 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 --model-id $model
``` ```