huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

increase semver

Browse Source
This commit is contained in:
OlivierDehaene 2023-02-03 12:25:20 +01:00
parent a7d15c38e8
commit 87dfc4e2c1
10 changed files with 25 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Cargo.lock generated
View File

@ -1888,7 +1888,7 @@ dependencies = [
[[package]]
name = "text-generation-client"
version = "0.1.0"
version = "0.2.0"
dependencies = [
"futures",
"prost",
@ -1903,7 +1903,7 @@ dependencies = [
[[package]]
name = "text-generation-launcher"
version = "0.1.0"
version = "0.2.0"
dependencies = [
"clap 4.0.22",
"ctrlc",
@ -1918,7 +1918,7 @@ dependencies = [
[[package]]
name = "text-generation-router"
version = "0.1.0"
version = "0.2.0"
dependencies = [
"async-stream",
"axum",

3
Cargo.toml
View File

@ -4,9 +4,6 @@ members = [
"router/client",
"launcher"
]
exclude = [
"server/safetensors",
]
[profile.release]
debug = 1

6
Makefile
View File

@ -15,6 +15,12 @@ server-dev:
router-dev:
cd router && cargo run
integration-tests: install-router install-launcher
cargo test
python-tests:
cd server && pytest tests
run-bloom-560m:
text-generation-launcher --model-id bigscience/bloom-560m --num-shard 2

8
README.md
View File

@ -33,6 +33,7 @@ to power LLMs api-inference widgets.
- [Run](#run)
- [Quantization](#quantization)
- [Develop](#develop)
- [Testing](#testing)
## Features
@ -146,3 +147,10 @@ make run-bloom-quantize # Requires 8xA100 40GB
make server-dev
make router-dev
```
## Testing
```shell
make python-tests
make integration-tests
```

2
docs/openapi.json
View File

@ -11,7 +11,7 @@
"name": "Apache 2.0",
"url": "https://www.apache.org/licenses/LICENSE-2.0"
},
"version": "0.1.0"
"version": "0.2.0"
},
"paths": {
"/generate": {

2
launcher/Cargo.toml
View File

@ -1,6 +1,6 @@
[package]
name = "text-generation-launcher"
version = "0.1.0"
version = "0.2.0"
edition = "2021"
authors = ["Olivier Dehaene"]
description = "Text Generation Launcher"

2
router/Cargo.toml
View File

@ -1,6 +1,6 @@
[package]
name = "text-generation-router"
version = "0.1.0"
version = "0.2.0"
edition = "2021"
authors = ["Olivier Dehaene"]
description = "Text Generation Webserver"

2
router/client/Cargo.toml
View File

@ -1,6 +1,6 @@
[package]
name = "text-generation-client"
version = "0.1.0"
version = "0.2.0"
edition = "2021"
[dependencies]

4
server/README.md
View File

@ -1,6 +1,6 @@
# BLOOM Inference Python gRPC Server
# Text Generation Inference Python gRPC Server
A Python gRPC server for BLOOM Inference
A Python gRPC server for Text Generation Inference
## Install

4
server/pyproject.toml
View File

@ -1,7 +1,7 @@
[tool.poetry]
name = "text-generation"
version = "0.1.0"
description = "BLOOM Inference Python gRPC Server"
version = "0.2.0"
description = "Text Generation Inference Python gRPC Server"
authors = ["Olivier Dehaene <olivier@huggingface.co>"]
[tool.poetry.scripts]