Add llm-vscode-inference-server

src/LLM.tex

@@ -540,3 +540,21 @@ pip install torch==1.13.1+cu116 --extra-index-url https://download.pytorch.org/w
 pip install -r requirements.txt
 python main.py --port 8080 --host 0.0.0.0 --pretrained "Phind/Phind-CodeLlama-34B-v2"
 \end{minted}
+
+\subsection{llm-vscode Inference Server}
+Perhaps.
+Uses vllm-project.
+
+\begin{minted}{sh}
+mkdir -p ~/devel/wangcx18
+cd ~/devel/wangcx18/
+git clone --recursive https://github.com/wangcx18/llm-vscode-inference-server
+cd llm-vscode-inference-server/
+virtualenv venv
+source venv/bin/activate
+pip install -U pip setuptools wheel
+#pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+pip install torch torchvision torchaudio
+pip install -r requirements.txt
+python api_server.py  --host 0.0.0.0 --port 8080
+\end{minted}