diff --git a/CHANGELOG.md b/CHANGELOG.md
index d58dfb45..c4e16192 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -18,6 +18,24 @@ This changelog is managed by towncrier and is compiled at release time.
 
 <!-- towncrier release notes start -->
 
+## [0.3.5](https://github.com/bentoml/openllm/tree/v0.3.5)
+
+### Features
+
+- Added support for continuous batching via vLLM
+
+  Currently benchmark shows that 100 concurrent requests shows around 1218 TPS on 1 A100 running meta-llama/Llama-2-13b-chat-hf
+  [#349](https://github.com/bentoml/openllm/issues/349)
+
+
+### Bug fix
+
+- Set a default serialisation for all models.
+
+  Currently, only Llama 2 will use safetensors as default format. For all other models, if they have safetensors format, then it will can be opt-int via `--serialisation safetensors`
+  [#355](https://github.com/bentoml/openllm/issues/355)
+
+
 ## [0.3.4](https://github.com/bentoml/openllm/tree/v0.3.4)
 
 ### Bug fix
diff --git a/changelog.d/349.feature.md b/changelog.d/349.feature.md
deleted file mode 100644
index 14d0bb97..00000000
--- a/changelog.d/349.feature.md
+++ /dev/null
@@ -1,3 +0,0 @@
-Added support for continuous batching via vLLM
-
-Currently benchmark shows that 100 concurrent requests shows around 1218 TPS on 1 A100 running meta-llama/Llama-2-13b-chat-hf
diff --git a/changelog.d/355.fix.md b/changelog.d/355.fix.md
deleted file mode 100644
index 68bb637b..00000000
--- a/changelog.d/355.fix.md
+++ /dev/null
@@ -1,3 +0,0 @@
-Set a default serialisation for all models.
-
-Currently, only Llama 2 will use safetensors as default format. For all other models, if they have safetensors format, then it will can be opt-int via `--serialisation safetensors`
diff --git a/openllm-contrib/clojure/package.json b/openllm-contrib/clojure/package.json
index 643700df..4dad5742 100644
--- a/openllm-contrib/clojure/package.json
+++ b/openllm-contrib/clojure/package.json
@@ -1,6 +1,6 @@
 {
   "name": "openllm-clojure-ui",
-  "version": "",
+  "version": "0.3.5",
   "description": "OpenLLM Clojure UI",
   "repository": {
     "url": "git@github.com:bentoml/OpenLLM.git",
diff --git a/openllm-node/package.json b/openllm-node/package.json
index 550852f3..61cbfab2 100644
--- a/openllm-node/package.json
+++ b/openllm-node/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@bentoml/openllm-node",
-  "version": "0.3.5.dev0",
+  "version": "0.3.5",
   "description": "NodeJS library for OpenLLM",
   "type": "module",
   "repository": {
diff --git a/openllm-python/CHANGELOG.md b/openllm-python/CHANGELOG.md
index d58dfb45..c4e16192 100644
--- a/openllm-python/CHANGELOG.md
+++ b/openllm-python/CHANGELOG.md
@@ -18,6 +18,24 @@ This changelog is managed by towncrier and is compiled at release time.
 
 <!-- towncrier release notes start -->
 
+## [0.3.5](https://github.com/bentoml/openllm/tree/v0.3.5)
+
+### Features
+
+- Added support for continuous batching via vLLM
+
+  Currently benchmark shows that 100 concurrent requests shows around 1218 TPS on 1 A100 running meta-llama/Llama-2-13b-chat-hf
+  [#349](https://github.com/bentoml/openllm/issues/349)
+
+
+### Bug fix
+
+- Set a default serialisation for all models.
+
+  Currently, only Llama 2 will use safetensors as default format. For all other models, if they have safetensors format, then it will can be opt-int via `--serialisation safetensors`
+  [#355](https://github.com/bentoml/openllm/issues/355)
+
+
 ## [0.3.4](https://github.com/bentoml/openllm/tree/v0.3.4)
 
 ### Bug fix
diff --git a/package.json b/package.json
index 43f98a62..c0f06cc2 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@bentoml/openllm-monorepo",
-  "version": "0.3.5.dev0",
+  "version": "0.3.5",
   "description": "OpenLLM: Operating LLMs in production",
   "author": "Aaron Pham <29749331+aarnphm@users.noreply.github.com>",
   "license": "Apache-2.0",