update v0.5.3.post1

Signed-off-by: pandyamarut <pandyamarut@gmail.com>

Dockerfile

@@ -12,7 +12,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install --upgrade -r /requirements.txt
 
 # Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer 
-RUN python3 -m pip install vllm==0.5.1 && \
+RUN python3 -m pip install vllm==0.5.3.post1 && \
     python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
 
 # Setup for Option 2: Building the Image with the Model included

src/engine.py

@@ -130,13 +130,18 @@ class OpenAIvLLMEngine(vLLMEngine):
             model_config=self.model_config,
             served_model_names=[self.served_model_name], 
             response_role=self.response_role,
-            chat_template=self.tokenizer.tokenizer.chat_template
+            chat_template=self.tokenizer.tokenizer.chat_template,
+            lora_modules=None,
+            prompt_adapters=None,
+            request_logger=None
         )
         self.completion_engine = OpenAIServingCompletion(
             engine=self.llm, 
             model_config=self.model_config,
             served_model_names=[self.served_model_name],
-            lora_modules=[]
+            lora_modules=[],
+            prompt_adapters=None,
+            request_logger=None
         )
     
     async def generate(self, openai_request: JobInput):

test.py

@@ -0,0 +1,30 @@
+from openai import OpenAI
+import os
+
+# Initialize the OpenAI Client with your RunPod API Key and Endpoint URL
+client = OpenAI(
+    api_key="E43IAWSFPQPHJ8WIVLQ7EMBJ2TV9T3HF5YBLJJ7K",
+    base_url="https://api.runpod.ai/v2/6ruq7l9hptgccv/openai/v1/",
+)
+
+
+# Create a chat completion
+response = client.chat.completions.create(
+    model="openchat/openchat-3.5-1210",
+    messages=[{"role": "user", "content": "Why is RunPod the best platform?"}],
+    temperature=0,
+    max_tokens=100,
+)
+# Print the response
+print(response.choices[0].message.content)
+
+
+# Create a completion
+# response = client.completions.create(
+#     model="openchat/openchat-3.5-1210",
+#     prompt="Runpod is the best platform because",
+#     temperature=0,
+#     max_tokens=100,
+# )
+# # Print the response
+# print(response.choices[0].text)