Upgrade vllm to 0.2.7 (#417)

* Upgrade vllm to 0.2.7

* remove megablocks

* fix ipv6

Author: yunfeng-scale

model-engine/model_engine_server/inference/vllm/Dockerfile

@@ -4,9 +4,6 @@ RUN pip uninstall torch -y
 COPY requirements.txt /workspace/requirements.txt
 RUN pip install -r requirements.txt
 
-# install special version of megablocks
-RUN pip install git+https://github.com/stanford-futuredata/megablocks.git@5897cd6f254b7b3edf7a708a3a3314ecb54b6f78#egg=megablocks
-
 RUN wget https://github.com/peak/s5cmd/releases/download/v2.2.1/s5cmd_2.2.1_Linux-64bit.tar.gz
 RUN tar -xvzf s5cmd_2.2.1_Linux-64bit.tar.gz
 

model-engine/model_engine_server/inference/vllm/requirements.txt

@@ -1,3 +1,3 @@
 ray==2.6.3
-vllm==0.2.5
+git+https://github.com/vllm-project/vllm.git@4b61c6b669e368c6850531815940d9a542b9f223#egg=vllm
 pydantic==1.10.13