diff --git a/docs/model_zoo.md b/docs/model_zoo.md
index 18610abbb..8805418cd 100644
--- a/docs/model_zoo.md
+++ b/docs/model_zoo.md
@@ -28,8 +28,14 @@ Scale hosts the following models in the LLM Engine Model Zoo:
 | `codellama-13b-instruct` | ✅                       | ✅                         | text-generation-inference, vllm            | 16384                                          |
 | `codellama-34b`          | ✅                       | ✅                         | text-generation-inference, vllm            | 16384                                          |
 | `codellama-34b-instruct` | ✅                       | ✅                         | text-generation-inference, vllm            | 16384                                          |
+| `codellama-70b`          | ✅                       |                            | vllm                                       | 16384                                          |
+| `codellama-70b-instruct` | ✅                       |                            | vllm                                       | 4096                                           |
 | `zephyr-7b-alpha`        | ✅                       |                            | text-generation-inference, vllm            | 32768                                          |
 | `zephyr-7b-beta`         | ✅                       |                            | text-generation-inference, vllm            | 32768                                          |
+| `gemma-2b`               | ✅                       |                            | vllm                                       | 8192                                           |
+| `gemma-2b-instruct`      | ✅                       |                            | vllm                                       | 8192                                           |
+| `gemma-7b`               | ✅                       |                            | vllm                                       | 8192                                           |
+| `gemma-7b-instruct`      | ✅                       |                            | vllm                                       | 8192                                           |
 
 ## Usage
 
diff --git a/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py b/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
index be56c7c54..ce2bf2657 100644
--- a/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
+++ b/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
@@ -185,6 +185,10 @@
             "mammoth-coder-llama-2-34b",
             "zephyr-7b-alpha",
             "zephyr-7b-beta",
+            "gemma-2b",
+            "gemma-2b-instruct",
+            "gemma-7b",
+            "gemma-7b-instruct",
         ]
     ),
     LLMInferenceFramework.LIGHTLLM: set(
@@ -223,6 +227,7 @@
     },  # setting both for backwards compatibility, will phase code-llama out in a future pr
     # Based on config here: https://huggingface.co/codellama/CodeLlama-7b-hf/blob/main/config.json#L12
     # Can also see 13B, 34B there too
+    "gemma": {"max_model_len": 8192, "max_num_batched_tokens": 8192},
     "llama-2": {"max_model_len": None, "max_num_batched_tokens": 4096},
     "mistral": {"max_model_len": 8000, "max_num_batched_tokens": 8000},
     "mixtral": {"max_model_len": 32768, "max_num_batched_tokens": 32768},
diff --git a/model-engine/model_engine_server/inference/vllm/requirements.txt b/model-engine/model_engine_server/inference/vllm/requirements.txt
index 4cc6239a4..78e033bbe 100644
--- a/model-engine/model_engine_server/inference/vllm/requirements.txt
+++ b/model-engine/model_engine_server/inference/vllm/requirements.txt
@@ -1,3 +1,3 @@
-ray==2.6.3
-git+https://github.com/vllm-project/vllm.git@4b61c6b669e368c6850531815940d9a542b9f223#egg=vllm
-pydantic==1.10.13
+ray>=2.9
+vllm==0.3.2
+pydantic>=2.0
diff --git a/model-engine/model_engine_server/infra/repositories/live_tokenizer_repository.py b/model-engine/model_engine_server/infra/repositories/live_tokenizer_repository.py
index 1140686fb..41356aefc 100644
--- a/model-engine/model_engine_server/infra/repositories/live_tokenizer_repository.py
+++ b/model-engine/model_engine_server/infra/repositories/live_tokenizer_repository.py
@@ -73,6 +73,10 @@ def get_default_supported_models_info() -> Dict[str, ModelInfo]:
         "vicuna-13b": ModelInfo("eachadea/vicuna-13b-1.1", None),
         "zephyr-7b-alpha": ModelInfo("HuggingFaceH4/zephyr-7b-alpha", None),
         "zephyr-7b-beta": ModelInfo("HuggingFaceH4/zephyr-7b-beta", None),
+        "gemma-2b": ModelInfo("google/gemma-2b", None),
+        "gemma-2b-instruct": ModelInfo("google/gemma-2b-it", None),
+        "gemma-7b": ModelInfo("google/gemma-7b", None),
+        "gemma-7b-instruct": ModelInfo("google/gemma-7b-it", None),
     }
 
 
diff --git a/model-engine/requirements.in b/model-engine/requirements.in
index eaa46f550..380f7ec97 100644
--- a/model-engine/requirements.in
+++ b/model-engine/requirements.in
@@ -51,9 +51,9 @@ sseclient-py==1.7.2
 stringcase==1.2.0
 tenacity>=6.0.0,<=6.2.0
 testing-postgresql==1.3.0
-transformers==4.34.1
+tokenizers~=0.15.2
 tqdm~=4.64
-transformers==4.34.1
+transformers==4.38.0
 twine==3.7.1
 uvicorn==0.17.6
 uvloop==0.17.0
diff --git a/model-engine/requirements.txt b/model-engine/requirements.txt
index 56acbaf9d..d4e6cd11c 100644
--- a/model-engine/requirements.txt
+++ b/model-engine/requirements.txt
@@ -190,7 +190,7 @@ hpack==4.0.0
     # via h2
 httptools==0.5.0
     # via -r model-engine/requirements.in
-huggingface-hub==0.17.3
+huggingface-hub==0.20.3
     # via
     #   tokenizers
     #   transformers
@@ -418,7 +418,7 @@ rsa==4.9
     # via google-auth
 s3transfer==0.6.1
     # via boto3
-safetensors==0.4.0
+safetensors==0.4.2
     # via transformers
 scramp==1.4.4
     # via pg8000
@@ -474,8 +474,10 @@ testing-common-database==2.0.3
     # via testing-postgresql
 testing-postgresql==1.3.0
     # via -r model-engine/requirements.in
-tokenizers==0.14.1
-    # via transformers
+tokenizers==0.15.2
+    # via
+    #   -r model-engine/requirements.in
+    #   transformers
 tomli==2.0.1
     # via
     #   build
@@ -487,7 +489,7 @@ tqdm==4.65.0
     #   huggingface-hub
     #   transformers
     #   twine
-transformers==4.34.1
+transformers==4.38.0
     # via -r model-engine/requirements.in
 twine==3.7.1
     # via -r model-engine/requirements.in