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

v0.9.4 (#713)

This commit is contained in:
OlivierDehaene 2023-07-27 19:25:15 +02:00 committed by GitHub
parent ab96b9aec3
commit 9f18f4c006
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Cargo.lock generated
View File

@ -2893,7 +2893,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-benchmark" name = "text-generation-benchmark"
version = "0.9.3" version = "0.9.4"
dependencies = [ dependencies = [
"average", "average",
"clap", "clap",
@ -2913,7 +2913,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-client" name = "text-generation-client"
version = "0.9.3" version = "0.9.4"
dependencies = [ dependencies = [
"futures", "futures",
"grpc-metadata", "grpc-metadata",
@ -2929,7 +2929,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-launcher" name = "text-generation-launcher"
version = "0.9.3" version = "0.9.4"
dependencies = [ dependencies = [
"clap", "clap",
"ctrlc", "ctrlc",
@ -2945,7 +2945,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-router" name = "text-generation-router"
version = "0.9.3" version = "0.9.4"
dependencies = [ dependencies = [
"async-stream", "async-stream",
"axum", "axum",

2
Cargo.toml
View File

@ -8,7 +8,7 @@ members = [
] ]
[workspace.package] [workspace.package]
version = "0.9.3" version = "0.9.4"
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

@ -84,7 +84,7 @@ The easiest way of getting started is using the official Docker container:
model=tiiuae/falcon-7b-instruct model=tiiuae/falcon-7b-instruct
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 ghcr.io/huggingface/text-generation-inference:0.9.3 --model-id $model docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.9.4 --model-id $model
``` ```
**Note:** 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. **Note:** 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.

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": "0.9.3" "version": "0.9.4"
}, },
"paths": { "paths": {
"/": { "/": {

2
server/pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "text-generation-server" name = "text-generation-server"
version = "0.9.3" version = "0.9.4"
description = "Text Generation Inference Python gRPC Server" description = "Text Generation Inference Python gRPC Server"
authors = ["Olivier Dehaene <olivier@huggingface.co>"] authors = ["Olivier Dehaene <olivier@huggingface.co>"]