[CI] change to quay.io (#102)

change docker registry to quay

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

.github/workflows/image.yml

@@ -39,25 +39,17 @@ jobs:
     steps:
     - uses: actions/checkout@v4
 
-    - name: Prepare
-      run: |
-        REPO_OWNER=$(echo "${{ github.repository_owner }}" | tr '[:upper:]' '[:lower:]')
-        echo "REPO_OWNER=${REPO_OWNER}" >> "$GITHUB_ENV"
-
     - name: Print
       run: |
-        echo "REPO_OWNER:""${REPO_OWNER}"
+        lscpu
 
     - name: Docker meta
       id: meta
       uses: docker/metadata-action@v5
       with:
         # TODO(yikun): add more hub image and a note on release policy for container image
-        # The REPO_OWNER will be:
-        # - `vllm-project` in usptream repo
-        # - lowercase github user in your fork repo
         images: |
-          ghcr.io/${{ env.REPO_OWNER }}/vllm-ascend
+          quay.io/ascend/vllm-ascend
         # Note for test case
         # https://github.com/marketplace/actions/docker-metadata-action#typeref
         # 1. branch job pulish per main/*-dev branch commits
@@ -87,12 +79,13 @@ jobs:
     - name: Build - Set up Docker Buildx
       uses: docker/setup-buildx-action@v2
 
-    - name: Publish - Login to GitHub Container Registry
-      uses: docker/login-action@v2
+    - name: Publish - Login to Quay Container Registry
+      if: ${{ github.event_name == 'push' }}
+      uses: docker/login-action@v3
       with:
-        registry: ghcr.io
-        username: ${{ github.actor }}
-        password: ${{ secrets.GITHUB_TOKEN }}
+        registry: quay.io
+        username: ${{ vars.QUAY_USERNAME }}
+        password: ${{ secrets.QUAY_PASSWORD }}
 
     - name: Build and push
       uses: docker/build-push-action@v6
@@ -104,3 +97,5 @@ jobs:
         push: ${{ github.event_name != 'pull_request' }}
         labels: ${{ steps.meta.outputs.labels }}
         tags: ${{ steps.meta.outputs.tags }}
+        build-args: |
+            PIP_INDEX_URL=https://pypi.org/simple

Dockerfile

@@ -17,6 +17,8 @@
 
 FROM quay.io/ascend/cann:8.0.0-910b-ubuntu22.04-py3.10
 
+ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
+
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 
@@ -29,7 +31,7 @@ WORKDIR /workspace
 
 COPY . /workspace/vllm-ascend/
 
-RUN pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
+RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM main
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
@@ -37,7 +39,7 @@ RUN git clone --depth 1 $VLLM_REPO /workspace/vllm
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install /workspace/vllm/
 
 # Install vllm-ascend main
-RUN python3 -m pip install /workspace/vllm-ascend/ -f https://download.pytorch.org/whl/torch/
+RUN python3 -m pip install /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/
 
 # Install modelscope
 RUN python3 -m pip install modelscope

docs/source/conf.py

@@ -68,7 +68,7 @@ myst_substitutions = {
     'vllm_ascend_version': 'main',
     # the newest release version of vllm, used in quick start or container image tag.
     # This value should be updated when cut down release.
-    'vllm_newest_release_version': "v0.7.1.rc1",
+    'vllm_newest_release_version': "v0.7.1rc1",
 }
 
 # Add any paths that contain templates here, relative to this directory.

docs/source/developer_guide/versioning_policy.md

@@ -51,7 +51,7 @@ Following is the Release Compatibility Matrix for vLLM Ascend Plugin:
 
 | vllm-ascend  | vLLM         | Python | Stable CANN | PyTorch/torch_npu |
 |--------------|--------------| --- | --- | --- |
-| v0.7.1.rc1 | v0.7.1 | 3.9 - 3.12 | 8.0.0   |  2.5.1 / 2.5.1.dev20250218 |
+| v0.7.1rc1 | v0.7.1 | 3.9 - 3.12 | 8.0.0   |  2.5.1 / 2.5.1.dev20250218 |
 
 ## Release cadence
 

docs/source/installation.md

@@ -119,10 +119,10 @@ You can install `vllm` and `vllm-ascend` from **pre-built wheel**:
 # It'll be fixed in the next vllm release, e.g. v0.7.3.
 git clone --branch v0.7.1 https://github.com/vllm-project/vllm
 cd vllm
-VLLM_TARGET_DEVICE=empty pip install . -f https://download.pytorch.org/whl/torch/
+VLLM_TARGET_DEVICE=empty pip install . --extra-index https://download.pytorch.org/whl/cpu/
 
 # Install vllm-ascend from pypi.
-pip install vllm-ascend -f https://download.pytorch.org/whl/torch/
+pip install vllm-ascend --extra-index https://download.pytorch.org/whl/cpu/
 
 # Once the packages are installed, you need to install `torch-npu` manually,
 # because that vllm-ascend relies on an unreleased version of torch-npu.
@@ -148,11 +148,11 @@ or build from **source code**:
 
 git clone  --depth 1 --branch |vllm_version| https://github.com/vllm-project/vllm
 cd vllm
-VLLM_TARGET_DEVICE=empty pip install . -f https://download.pytorch.org/whl/torch/
+VLLM_TARGET_DEVICE=empty pip install . --extra-index https://download.pytorch.org/whl/cpu/
 
 git clone  --depth 1 --branch |vllm_ascend_version| https://github.com/vllm-project/vllm-ascend.git
 cd vllm-ascend
-pip install -e . -f https://download.pytorch.org/whl/torch/
+pip install -e . --extra-index https://download.pytorch.org/whl/cpu/
 ```
 
 ::::

docs/source/quick_start.md

@@ -12,7 +12,7 @@
    :substitutions:
 
 # You can change version a suitable one base on your requirement, e.g. main
-export IMAGE=ghcr.io/vllm-project/vllm-ascend:|vllm_newest_release_version|
+export IMAGE=quay.io/ascend:|vllm_newest_release_version|
 
 docker run \
 --name vllm-ascend \

docs/source/tutorials.md

@@ -20,7 +20,7 @@ docker run \
 -v /etc/ascend_install.info:/etc/ascend_install.info \
 -v /root/.cache:/root/.cache \
 -p 8000:8000 \
--it ghcr.io/vllm-project/vllm-ascend:v0.7.1.rc1 bash
+-it quay.io/ascend/vllm-ascend:v0.7.1rc1 bash
 ```
 
 Setup environment variables:
@@ -83,7 +83,7 @@ docker run \
 -p 8000:8000 \
 -e VLLM_USE_MODELSCOPE=True \
 -e PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 \
--it ghcr.io/vllm-project/vllm-ascend:v0.7.1.rc1 \
+-it quay.io/ascend/vllm-ascend:v0.7.1rc1 \
 vllm serve Qwen/Qwen2.5-7B-Instruct --max_model_len 26240
 ```
 
@@ -146,7 +146,7 @@ docker run \
 -v /etc/ascend_install.info:/etc/ascend_install.info \
 -v /root/.cache:/root/.cache \
 -p 8000:8000 \
--it ghcr.io/vllm-project/vllm-ascend:v0.7.1.rc1 bash
+-it quay.io/ascend/vllm-ascend:v0.7.1rc1 bash
 ```
 
 Setup environment variables:

docs/source/user_guide/release_notes.md

@@ -1,6 +1,6 @@
 # Release note
 
-## v0.7.1.rc1
+## v0.7.1rc1
 
 🎉 Hello, World!
 
@@ -29,6 +29,6 @@ Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/v0.7.1rc1
 
 ### Known issues
 
-- This release relies on an unreleased torch_npu version. It has been installed within official container image already. Please [install](https://vllm-ascend.readthedocs.io/en/v0.7.1.rc1/installation.html) it manually if you are using non-container environment.
+- This release relies on an unreleased torch_npu version. It has been installed within official container image already. Please [install](https://vllm-ascend.readthedocs.io/en/v0.7.1rc1/installation.html) it manually if you are using non-container environment.
 - There are logs like `No platform deteced, vLLM is running on UnspecifiedPlatform` or `Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'")` shown when runing vllm-ascend. It actually doesn't affect any functionality and performance. You can just ignore it. And it has been fixed in this [PR](https://github.com/vllm-project/vllm/pull/12432) which will be included in v0.7.3 soon.
 - There are logs like `# CPU blocks: 35064, # CPU blocks: 2730` shown when runing vllm-ascend which should be `# NPU blocks:` . It actually doesn't affect any functionality and performance. You can just ignore it. And it has been fixed in this [PR](https://github.com/vllm-project/vllm/pull/13378) which will be included in v0.7.3 soon.