increase semver

Cargo.lock

@@ -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",

Cargo.toml

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

Makefile

@@ -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
 

README.md

@@ -33,6 +33,7 @@ to power LLMs api-inference widgets.
   - [Run](#run)
   - [Quantization](#quantization)
 - [Develop](#develop)
+- [Testing](#testing)
   
 ## Features
 
@@ -145,4 +146,11 @@ make run-bloom-quantize # Requires 8xA100 40GB
 ```shell
 make server-dev
 make router-dev
+```
+
+## Testing
+
+```shell
+make python-tests
+make integration-tests
 ```

docs/openapi.json

@@ -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": {

launcher/Cargo.toml

@@ -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"

router/Cargo.toml

@@ -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"

router/client/Cargo.toml

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

server/README.md

@@ -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
 

server/pyproject.toml

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