diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 5fabaa9..a08474b 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -110,3 +110,4 @@ jobs:
           artifacts: "tabby_*/tabby_*"
           tag: ${{ github.ref_name }}
           removeArtifacts: true
+          bodyFile: ci/RELEASE_NOTES.md
diff --git a/ci/RELEASE_NOTES.md b/ci/RELEASE_NOTES.md
new file mode 100644
index 0000000..586f1d5
--- /dev/null
+++ b/ci/RELEASE_NOTES.md
@@ -0,0 +1,19 @@
+## 📦 Artifacts
+* Binary for Mac OSX M1/M2, CPU only: [tabby_aarch64-apple-darwin](https://github.com/TabbyML/tabby/releases/download/v0.0.1-rc.2/tabby_aarch64-apple-darwin).
+* Binary for Linux x86/64, CPU only: [tabby_x86_64-unknown-linux-gnu](https://github.com/TabbyML/tabby/releases/download/v0.0.1-rc.2/tabby_x86_64-unknown-linux-gnu).
+* Docker image with NVIDIA CUDA Support: [tabbyml/tabby:0.0.1-rc.2](https://hub.docker.com/layers/tabbyml/tabby/0.0.1-rc.2/images/sha256-7de5477377bc493fe7e3c7871dc0f9ae83beaefef5ad3da065ae66c54fec88b1?context=explore).
+
+## 🚀 Features
+* Support FIM inference.
+* Initial support of indexing with `tabby scheduler`.
+* Support CodeLlama series model.
+
+## 🧰 Improvements
+* Support early cancellation to reduce GPU workload, increasing capacity of tabby server.
+
+## 💫 New Contributors
+* @Allesanddro made their first contribution in https://github.com/TabbyML/tabby/pull/233
+* @prologic made their first contribution in https://github.com/TabbyML/tabby/pull/250
+* @pauchiner made their first contribution in https://github.com/TabbyML/tabby/pull/253
+* @ghthor made their first contribution in https://github.com/TabbyML/tabby/pull/255
+* @sandrofigo made their first contribution in https://github.com/TabbyML/tabby/pull/353