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:
6b46c4b653

---------

Signed-off-by: mywaaagh_admin <pkwarcraft@gmail.com>

.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: |