From 081b92658470bf5b40aec7427e084b7a96c8fbd2 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Tue, 30 May 2023 18:39:35 +0200
Subject: [PATCH] v0.8.0

---
 Cargo.lock            | 8 ++++----
 Cargo.toml            | 2 +-
 README.md             | 7 +++++--
 docs/openapi.json     | 2 +-
 server/pyproject.toml | 2 +-
 supported_models.json | 9 ---------
 6 files changed, 12 insertions(+), 18 deletions(-)
 delete mode 100644 supported_models.json

diff --git a/Cargo.lock b/Cargo.lock
index 62896a515db..cddebd6150b 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2557,7 +2557,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.7.0"
+version = "0.8.0"
 dependencies = [
  "average",
  "clap",
@@ -2577,7 +2577,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.7.0"
+version = "0.8.0"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2593,7 +2593,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.7.0"
+version = "0.8.0"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2609,7 +2609,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.7.0"
+version = "0.8.0"
 dependencies = [
  "async-stream",
  "axum",
diff --git a/Cargo.toml b/Cargo.toml
index 4ed0524e8de..871fc6881fe 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.7.0"
+version = "0.8.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/README.md b/README.md
index 30e085b253a..8c8d9773703 100644
--- a/README.md
+++ b/README.md
@@ -42,7 +42,7 @@ to power LLMs api-inference widgets.
 - Serve the most popular Large Language Models with a simple launcher
 - Tensor Parallelism for faster inference on multiple GPUs
 - Token streaming using Server-Sent Events (SSE)
-- [Continous batching of incoming requests](https://github.com/huggingface/text-generation-inference/tree/main/router) for increased total throughput
+- [Continuous batching of incoming requests](https://github.com/huggingface/text-generation-inference/tree/main/router) for increased total throughput
 - Optimized transformers code for inference using [flash-attention](https://github.com/HazyResearch/flash-attention) on the most popular architectures
 - Quantization with [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)
 - [Safetensors](https://github.com/huggingface/safetensors) weight loading
@@ -61,6 +61,9 @@ to power LLMs api-inference widgets.
 - [Llama](https://github.com/facebookresearch/llama)
 - [OPT](https://huggingface.co/facebook/opt-66b)
 - [SantaCoder](https://huggingface.co/bigcode/santacoder)
+- [Starcoder](https://huggingface.co/bigcode/starcoder)
+- [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b)
+- [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b)
 
 Other architectures are supported on a best effort basis using:
 
@@ -81,7 +84,7 @@ model=bigscience/bloom-560m
 num_shard=2
 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:0.7 --model-id $model --num-shard $num_shard
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.8 --model-id $model --num-shard $num_shard
 ```
 **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.
 
diff --git a/docs/openapi.json b/docs/openapi.json
index 5bccc9fc3a4..965aefd2a7a 100644
--- a/docs/openapi.json
+++ b/docs/openapi.json
@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "0.7.0"
+    "version": "0.8.0"
   },
   "paths": {
     "/": {
diff --git a/server/pyproject.toml b/server/pyproject.toml
index d674172d83e..28e078b0c1f 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.7.0"
+version = "0.8.0"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]
 
diff --git a/supported_models.json b/supported_models.json
deleted file mode 100644
index 8e9dd9e03bd..00000000000
--- a/supported_models.json
+++ /dev/null
@@ -1,9 +0,0 @@
-[
-  "bigcode/santacoder",
-  "bigscience/bloom",
-  "bigscience/bloomz",
-  "EleutherAI/gpt-neox-20b",
-  "google/flan-ul2",
-  "google/flan-t5-xxl",
-  "OpenAssistant/oasst-sft-1-pythia-12b"
-]