From ff97740b8d68f337707494ae0221bb7cc15f4f82 Mon Sep 17 00:00:00 2001 From: li chaoran Date: Thu, 24 Jul 2025 10:47:05 +0800 Subject: [PATCH] Use mirror images (#1912) ### What this PR does / why we need it? More discussion can be found [here](https://github.com/ascend-gha-runners/docs/issues/23). The infra team deployed a internal registry since both `m.daocloud.io` and `quay.io` suffered a unstable connect quality. CI will benefit both the connection and download speed by switching to the internal registry. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? tested locally - vLLM version: v0.9.2 - vLLM main: https://github.com/vllm-project/vllm/commit/6b46c4b653d1d730a9b75d32b59b9d60f879b9d7 --------- Signed-off-by: mywaaagh_admin --- .github/workflows/accuracy_test.yaml | 2 +- .github/workflows/nightly_benchmarks.yaml | 2 +- .github/workflows/vllm_ascend_doctest.yaml | 2 +- .github/workflows/vllm_ascend_test.yaml | 6 ++---- .github/workflows/vllm_ascend_test_long_term.yaml | 3 +-- .github/workflows/vllm_ascend_test_pd.yaml | 2 +- 6 files changed, 7 insertions(+), 10 deletions(-) diff --git a/.github/workflows/accuracy_test.yaml b/.github/workflows/accuracy_test.yaml index f7361ea..1fe73f3 100644 --- a/.github/workflows/accuracy_test.yaml +++ b/.github/workflows/accuracy_test.yaml @@ -123,7 +123,7 @@ jobs: fail-fast: false name: ${{ matrix.model_name }} accuracy container: - image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10 env: DATASET_SOURCE: ModelScope VLLM_USE_MODELSCOPE: True diff --git a/.github/workflows/nightly_benchmarks.yaml b/.github/workflows/nightly_benchmarks.yaml index ddfa1b1..16d57a3 100644 --- a/.github/workflows/nightly_benchmarks.yaml +++ b/.github/workflows/nightly_benchmarks.yaml @@ -56,7 +56,7 @@ jobs: vllm_use_v1: 1 max-parallel: 1 container: - image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10 volumes: - /usr/local/dcmi:/usr/local/dcmi - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi diff --git a/.github/workflows/vllm_ascend_doctest.yaml b/.github/workflows/vllm_ascend_doctest.yaml index dc11886..25746db 100644 --- a/.github/workflows/vllm_ascend_doctest.yaml +++ b/.github/workflows/vllm_ascend_doctest.yaml @@ -50,7 +50,7 @@ jobs: name: vLLM Ascend test runs-on: linux-arm64-npu-1 container: - image: m.daocloud.io/quay.io/ascend/vllm-ascend:${{ matrix.vllm_verison }} + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:${{ matrix.vllm_verison }} steps: - name: Check NPU/CANN and git info run: | diff --git a/.github/workflows/vllm_ascend_test.yaml b/.github/workflows/vllm_ascend_test.yaml index 7caadfd..5a361a3 100644 --- a/.github/workflows/vllm_ascend_test.yaml +++ b/.github/workflows/vllm_ascend_test.yaml @@ -141,8 +141,7 @@ jobs: name: singlecard e2e test runs-on: ${{ matrix.os }} container: - # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready - image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True @@ -221,8 +220,7 @@ jobs: name: multicard e2e test runs-on: ${{ matrix.os }} container: - # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready - image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True diff --git a/.github/workflows/vllm_ascend_test_long_term.yaml b/.github/workflows/vllm_ascend_test_long_term.yaml index 698a61b..959e9c2 100644 --- a/.github/workflows/vllm_ascend_test_long_term.yaml +++ b/.github/workflows/vllm_ascend_test_long_term.yaml @@ -47,8 +47,7 @@ jobs: name: vLLM Ascend long term test runs-on: ${{ matrix.os }} container: - # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready - image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True diff --git a/.github/workflows/vllm_ascend_test_pd.yaml b/.github/workflows/vllm_ascend_test_pd.yaml index 17da445..924a543 100644 --- a/.github/workflows/vllm_ascend_test_pd.yaml +++ b/.github/workflows/vllm_ascend_test_pd.yaml @@ -50,7 +50,7 @@ jobs: runs-on: linux-arm64-npu-static-8 container: - image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10 volumes: - /usr/local/dcmi:/usr/local/dcmi - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi