[CI] Use offline mode for nightly test (#5187)

### What this PR does / why we need it?
For single node test, the lack of a retry mechanism for accessing
ModelScope resulted in an HTTP 400 error sometimes. I recommend using a
local offline cache instead.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangli <wangli858794774@gmail.com>

.github/workflows/_e2e_nightly_single_node.yaml

@@ -57,6 +57,9 @@ jobs:
     timeout-minutes: 600
     container:
       image: ${{ inputs.image }}
+    env:
+      TRANSFORMERS_OFFLINE: 1
+      VLLM_USE_MODELSCOPE: True
     steps:
       - name: Check npu and CANN info
         run: |

.github/workflows/pr_tag_image_build_and_push.yaml

@@ -26,7 +26,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
-    types: [ labeled, synchronize ]
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:

tests/e2e/conftest.py

@@ -162,7 +162,7 @@ class RemoteOpenAIServer:
         self.proxy_port = proxy_port
 
         self._start_server(model, vllm_serve_args, env_dict)
-        max_wait_seconds = max_wait_seconds or 1800
+        max_wait_seconds = max_wait_seconds or 2800
         if self.disaggregated_prefill:
             assert proxy_port is not None, "for disaggregated_prefill, proxy port must be provided"
             self._wait_for_server_pd(timeout=max_wait_seconds)