Release v0.2.1 (#72)

Author: JoeZijunZhou

docs/online-inference-with-maxtext-engine.md

@@ -21,8 +21,8 @@ Follow the steps in [Manage TPU resources | Google Cloud](https://cloud.google.c
 ## Step 1: Download JetStream and the MaxText github repository
 
 ```bash
-git clone -b jetstream-v0.2.0 https://github.com/google/maxtext.git
-git clone -b v0.2.0 https://github.com/google/JetStream.git
+git clone -b jetstream-v0.2.1 https://github.com/google/maxtext.git
+git clone -b v0.2.1 https://github.com/google/JetStream.git
 ```
 
 ## Step 2: Setup MaxText

setup.py

@@ -24,7 +24,7 @@ def parse_requirements(filename):
 
 setup(
     name="google-jetstream",
-    version="0.2.0",
+    version="0.2.1",
     description=(
         "JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome)."
     ),