From ecb16dcf14ed6ce153baeab0331214ecd87af962 Mon Sep 17 00:00:00 2001
From: binbin Deng <108676127+plusbang@users.noreply.github.com>
Date: Tue, 21 May 2024 14:49:54 +0800
Subject: [PATCH] Add deepspeed autotp support for xpu docker (#11077)

---
 docker/llm/inference/xpu/docker/Dockerfile | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/docker/llm/inference/xpu/docker/Dockerfile b/docker/llm/inference/xpu/docker/Dockerfile
index 0146e9f2..77022558 100644
--- a/docker/llm/inference/xpu/docker/Dockerfile
+++ b/docker/llm/inference/xpu/docker/Dockerfile
@@ -53,12 +53,20 @@ RUN curl -fsSL https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-P
     pip install --upgrade fastapi && \
     pip install --upgrade "uvicorn[standard]" && \
     # Download vLLM-Serving
-    git clone https://github.com/intel-analytics/IPEX-LLM && \
-    cp -r ./IPEX-LLM/python/llm/example/GPU/vLLM-Serving/ ./vLLM-Serving && \
-    rm -rf ./IPEX-LLM && \
+    cp -r ./ipex-llm/python/llm/example/GPU/vLLM-Serving/ ./vLLM-Serving && \
     # Install related library of benchmarking
-    pip install pandas && \
-    pip install omegaconf && \
-    chmod +x /llm/benchmark.sh
+    pip install pandas omegaconf && \
+    chmod +x /llm/benchmark.sh && \
+    # Download Deepspeed-AutoTP
+    cp -r ./ipex-llm/python/llm/example/GPU/Deepspeed-AutoTP/ ./Deepspeed-AutoTP && \
+    # Install related library of Deepspeed-AutoTP
+    pip install oneccl_bind_pt==2.1.100 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ && \
+    pip install git+https://github.com/microsoft/DeepSpeed.git@ed8aed5 && \
+    pip install git+https://github.com/intel/intel-extension-for-deepspeed.git@0eb734b && \
+    pip install mpi4py && \
+    apt-get update && \
+    apt-get install -y google-perftools && \
+    ln -s /usr/local/lib/python3.11/dist-packages/ipex_llm/libs/libtcmalloc.so /lib/libtcmalloc.so && \
+    rm -rf ./ipex-llm
 
 WORKDIR /llm/