[ci] feat: add ci timeout (#487)

Set timeout in CI to avoid infinite hang.
close #468

.github/workflows/e2e_ascend.yml

@@ -22,6 +22,7 @@ jobs:
   test:
     name: verl Ascend test (self-host)
     runs-on: [self-hosted, npu-0]
+    timeout-minutes: 5 # Increase this timeout value as needed
     env:
       HF_HUB_ENABLE_HF_TRANSFER: 1
     container:

.github/workflows/e2e_digit_completion.yml

@@ -27,6 +27,7 @@ permissions:
 jobs:
   e2e_digit_completion:
     runs-on: [self-hosted, l20-0]
+    timeout-minutes: 10 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/e2e_digit_completion_fire.yml

@@ -24,6 +24,7 @@ permissions:
 jobs:
   e2e_digit_completion:
     runs-on: [self-hosted, l20-0]
+    timeout-minutes: 10 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/e2e_gsm8k.yml

@@ -27,6 +27,7 @@ permissions:
 jobs:
   e2e_gsm8k:
     runs-on: [self-hosted, l20-1]
+    timeout-minutes: 40 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/e2e_gsm8k_megatron.yml

@@ -28,6 +28,7 @@ permissions:
 jobs:
   e2e_gsm8k_megatron:
     runs-on: [self-hosted, l20-0]
+    timeout-minutes: 20 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/e2e_lora.yml

@@ -26,6 +26,7 @@ permissions:
 jobs:
   e2e_lora:
     runs-on: [self-hosted, l20-1]
+    timeout-minutes: 5 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/e2e_sft.yml

@@ -26,6 +26,7 @@ permissions:
 jobs:
   e2e_sft:
     runs-on: [self-hosted, l20-1]
+    timeout-minutes: 5 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/e2e_vlm_geo3k.yml

@@ -26,6 +26,7 @@ permissions:
 jobs:
   e2e_vlm_geo3k:
     runs-on: [self-hosted, l20-1]
+    timeout-minutes: 10 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/model.yml

@@ -25,6 +25,7 @@ permissions:
 jobs:
   model_rmpad:
     runs-on: [self-hosted, l20-1]
+    timeout-minutes: 5 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/ray_test.yml

@@ -25,6 +25,7 @@ permissions:
 jobs:
   ray:
     runs-on: [self-hosted, l20-0]
+    timeout-minutes: 5 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/sandbox.yml

@@ -25,6 +25,7 @@ permissions:
 jobs:
   sandbox:
     runs-on: [self-hosted, l20-0]
+    timeout-minutes: 3 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}

.github/workflows/sanity.yml

@@ -25,6 +25,7 @@ permissions:
 jobs:
   sanity:
     runs-on: ubuntu-latest
+    timeout-minutes: 5 # Increase this timeout value as needed
     strategy:
       matrix:
         python-version: ["3.10"]

.github/workflows/vllm.yml

@@ -26,6 +26,7 @@ permissions:
 jobs:
   vllm:
     runs-on: [self-hosted, l20-0]
+    timeout-minutes: 20 # Increase this timeout value as needed
     env:
       HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
       HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}