From f37547249d204e6b44e809c5539733fcfacacc16 Mon Sep 17 00:00:00 2001
From: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Date: Tue, 24 Oct 2023 12:56:03 +0800
Subject: [PATCH] Refine README/CICD (#9253)

---
 .github/workflows/manually_build.yml       | 7 ++++++-
 python/llm/src/bigdl/llm/serving/README.md | 4 +++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/manually_build.yml b/.github/workflows/manually_build.yml
index 47394651..0601b2d0 100644
--- a/.github/workflows/manually_build.yml
+++ b/.github/workflows/manually_build.yml
@@ -876,18 +876,23 @@ jobs:
         echo "##############################################################"
         echo "############## bigdl-ppml-trusted-bigdl-llm-serving-tdx ###############"
         echo "##############################################################"
-        export image=intelanalytics/bigdl-ppml-trusted-bigdl-llm-serving-tdx
+        export image=intelanalytics/trusted-bigdl-llm-serving-tdx
+        export base_image=intelanalytics/bigdl-llm-serving-cpu
+        docker pull ${base_image}:${TAG}
         cd ppml/tdx/docker/trusted-bigdl-llm/serving/docker
         sudo docker build \
           --no-cache=true \
           --build-arg http_proxy=${HTTP_PROXY} \
           --build-arg https_proxy=${HTTPS_PROXY} \
+          --build-arg BASE_IMAGE_NAME=${base_image} \
+          --build-arg BASE_IMAGE_TAG=${TAG} \
           --build-arg no_proxy=${NO_PROXY} \
           -t ${image}:${TAG} -f ./Dockerfile .
         sudo docker push ${image}:${TAG}
         sudo docker tag ${image}:${TAG} 10.239.45.10/arda/${image}:${TAG}
         sudo docker push 10.239.45.10/arda/${image}:${TAG}
         sudo docker rmi -f ${image}:${TAG} 10.239.45.10/arda/${image}:${TAG}
+        sudo docker rmi -f ${base_image}:${TAG}
 
   bigdl-ppml-trusted-bigdl-llm-tdx:
     if: ${{ github.event.inputs.artifact == 'bigdl-ppml-trusted-bigdl-llm-tdx' || github.event.inputs.artifact == 'all' }}
diff --git a/python/llm/src/bigdl/llm/serving/README.md b/python/llm/src/bigdl/llm/serving/README.md
index 14aa0253..e967f3da 100644
--- a/python/llm/src/bigdl/llm/serving/README.md
+++ b/python/llm/src/bigdl/llm/serving/README.md
@@ -38,7 +38,9 @@ Using BigDL-LLM in FastChat does not impose any new limitations on model usage.
 FastChat determines the Model adapter to use through path matching. Therefore, in order to load models using BigDL-LLM, you need to make some modifications to the model's name.
 
 For instance, assuming you have downloaded the `llama-7b-hf` from [HuggingFace](https://huggingface.co/decapoda-research/llama-7b-hf).  Then, to use the `BigDL-LLM` as backend, you need to change name from `llama-7b-hf` to `bigdl-7b`.
-The key point here is that the model's path should include "bigdl" and should not include paths matched by other model adapters.
+The key point here is that the model's path should include "bigdl" and **should not include paths matched by other model adapters**.
+
+> note: This is caused by the priority of name matching list. The new added `BigDL-LLM` adapter is at the tail of the name-matching list so that it has the lowest priority. If model path contains other keywords like `vicuna` which matches to another adapter with higher priority, then the `BigDL-LLM` adapter will not work.
 
 A special case is `ChatGLM` models. For these models, you do not need to do any changes after downloading the model and the `BigDL-LLM` backend will be used automatically.