v0.9.3 (#634)

Cargo.lock

@@ -2893,7 +2893,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.9.2"
+version = "0.9.3"
 dependencies = [
  "average",
  "clap",
@@ -2913,7 +2913,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.9.2"
+version = "0.9.3"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2929,7 +2929,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.9.2"
+version = "0.9.3"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2945,7 +2945,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.9.2"
+version = "0.9.3"
 dependencies = [
  "async-stream",
  "axum",

Cargo.toml

@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.9.2"
+version = "0.9.3"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

README.md

@@ -63,6 +63,8 @@ to power LLMs api-inference widgets.
 - [Starcoder](https://huggingface.co/bigcode/starcoder)
 - [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b)
 - [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b)
+- [MPT](https://huggingface.co/mosaicml/mpt-30b)
+- [Llama V2](https://huggingface.co/meta-llama)
 
 Other architectures are supported on a best effort basis using:
 

docs/openapi.json

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "0.9.2"
+    "version": "0.9.3"
   },
   "paths": {
     "/": {

server/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.9.2"
+version = "0.9.3"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]