fix

.cuda_ext.json

@@ -2,11 +2,11 @@
   "build": [
     {
       "torch_command": "pip install torch==2.3.0 torchvision==0.18.0 torchaudio==2.3.0 --index-url https://download.pytorch.org/whl/cu121",
-      "cuda_image": "hpcaitech/cuda-conda:12.1"
+      "cuda_image": "image-cloud.luchentech.com/hpcaitech/cuda-conda:12.1"
     },
     {
       "torch_command": "pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu124",
-      "cuda_image": "hpcaitech/cuda-conda:12.4"
+      "cuda_image": "image-cloud.luchentech.com/hpcaitech/cuda-conda:12.4"
     }
   ]
 }

.github/workflows/build_on_schedule.yml

@@ -12,7 +12,7 @@ jobs:
     if: github.repository == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /dev/shm -v /data/scratch/:/data/scratch/
     timeout-minutes: 90
     steps:

.github/workflows/close_inactive.yml

@@ -7,7 +7,7 @@ on:
 jobs:
   close-issues:
     if: github.event.pull_request.draft == false && github.base_ref == 'main' && github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     permissions:
       issues: write
       pull-requests: write

.github/workflows/compatiblity_test_on_dispatch.yml

@@ -15,7 +15,7 @@ on:
 jobs:
   matrix_preparation:
     name: Prepare Container List
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     steps:
@@ -31,7 +31,7 @@ jobs:
           do
               for cv in $CUDA_VERSIONS
               do
-                  DOCKER_IMAGE+=("\"hpcaitech/pytorch-cuda:${tv}-${cv}\"")
+                  DOCKER_IMAGE+=("\"image-cloud.luchentech.com/hpcaitech/pytorch-cuda:${tv}-${cv}\"")
               done
           done
 
@@ -44,7 +44,7 @@ jobs:
     name: Test for PyTorch Compatibility
     needs: matrix_preparation
     if: github.repository == 'hpcaitech/ColossalAI'
-    runs-on: [self-hosted, 8-gpu]
+    runs-on: [self-hosted, ubuntu-latest]
     strategy:
       fail-fast: false
       matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}

.github/workflows/compatiblity_test_on_pr.yml

@@ -9,7 +9,7 @@ on:
 jobs:
   matrix_preparation:
     name: Prepare Container List
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     concurrency:
@@ -23,7 +23,7 @@ jobs:
           DOCKER_IMAGE=()
 
           while read tag; do
-            DOCKER_IMAGE+=("\"hpcaitech/pytorch-cuda:${tag}\"")
+            DOCKER_IMAGE+=("\"image-cloud.luchentech.com/hpcaitech/pytorch-cuda:${tag}\"")
           done <.compatibility
 
           container=$( IFS=',' ; echo "${DOCKER_IMAGE[*]}" )
@@ -35,7 +35,7 @@ jobs:
     name: Test for PyTorch Compatibility
     needs: matrix_preparation
     if: github.repository == 'hpcaitech/ColossalAI'
-    runs-on: [self-hosted, 8-gpu]
+    runs-on: [self-hosted, ubuntu-latest]
     strategy:
       fail-fast: false
       matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}

.github/workflows/compatiblity_test_on_schedule.yml

@@ -9,7 +9,7 @@ on:
 jobs:
   matrix_preparation:
     name: Prepare Container List
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     steps:
@@ -20,7 +20,7 @@ jobs:
           DOCKER_IMAGE=()
 
           while read tag; do
-            DOCKER_IMAGE+=("\"hpcaitech/pytorch-cuda:${tag}\"")
+            DOCKER_IMAGE+=("\"image-cloud.luchentech.com/hpcaitech/pytorch-cuda:${tag}\"")
           done <.compatibility
 
           container=$( IFS=',' ; echo "${DOCKER_IMAGE[*]}" )
@@ -32,7 +32,7 @@ jobs:
     name: Test for PyTorch Compatibility
     needs: matrix_preparation
     if: github.repository == 'hpcaitech/ColossalAI'
-    runs-on: [self-hosted, 8-gpu]
+    runs-on: [self-hosted, ubuntu-latest]
     strategy:
       fail-fast: false
       matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}

.github/workflows/doc_build_on_schedule_after_release.yml

@@ -11,7 +11,7 @@ jobs:
   build-doc:
     name: Trigger Documentation Build Workflow
     if: github.repository == 'hpcaitech/ColossalAI'
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     steps:
       - name: trigger workflow in ColossalAI-Documentation
         run: |

.github/workflows/doc_check_on_pr.yml

@@ -15,7 +15,7 @@ jobs:
     if: |
       github.event.pull_request.draft == false &&
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     concurrency:
       group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-check-i18n
       cancel-in-progress: true
@@ -33,7 +33,7 @@ jobs:
     if: |
       github.event.pull_request.draft == false &&
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     concurrency:
       group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-check-doc
       cancel-in-progress: true

.github/workflows/doc_test_on_pr.yml

@@ -15,7 +15,7 @@ jobs:
     if: |
       github.event.pull_request.draft == false &&
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request'
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     outputs:
       any_changed: ${{ steps.changed-files.outputs.any_changed }}
       changed_files: ${{ steps.changed-files.outputs.all_changed_files }}
@@ -56,7 +56,7 @@ jobs:
     needs: detect-changed-doc
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm
     timeout-minutes: 30
     defaults:

.github/workflows/doc_test_on_schedule.yml

@@ -12,7 +12,7 @@ jobs:
     name: Test the changed Doc
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm
     timeout-minutes: 60
     steps:

.github/workflows/draft_github_release_post_after_merge.yml

@@ -12,7 +12,7 @@ jobs:
   release:
     name: Draft Release Post
     if: ( github.event_name == 'workflow_dispatch' || github.event.pull_request.merged == true ) && github.repository == 'hpcaitech/ColossalAI'
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     steps:
       - uses: actions/checkout@v2
         with:

.github/workflows/example_check_on_dispatch.yml

@@ -14,7 +14,7 @@ jobs:
         github.base_ref == 'main' &&
         github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     name: Check the examples user want
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     steps:
@@ -45,7 +45,7 @@ jobs:
       fail-fast: false
       matrix: ${{fromJson(needs.manual_check_matrix_preparation.outputs.matrix)}}
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/ -v /dev/shm
     timeout-minutes: 15
     steps:

.github/workflows/example_check_on_pr.yml

@@ -17,7 +17,7 @@ jobs:
     if: |
       github.event.pull_request.draft == false &&
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request'
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     outputs:
       matrix: ${{ steps.setup-matrix.outputs.matrix }}
       anyChanged: ${{ steps.setup-matrix.outputs.anyChanged }}
@@ -90,7 +90,7 @@ jobs:
       fail-fast: false
       matrix: ${{fromJson(needs.detect-changed-example.outputs.matrix)}}
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/ -v /dev/shm
     timeout-minutes: 30
     concurrency:

.github/workflows/example_check_on_schedule.yml

@@ -10,7 +10,7 @@ jobs:
   matrix_preparation:
     if: github.repository == 'hpcaitech/ColossalAI'
     name: Prepare matrix for weekly check
-    runs-on: ubuntu-latest
+    runs-on: ubunt[self-hosted, ubuntu-latest]u-latest
     outputs:
       matrix: ${{ steps.setup-matrix.outputs.matrix }}
     steps:
@@ -34,7 +34,7 @@ jobs:
       fail-fast: false
       matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/ -v /dev/shm
     timeout-minutes: 30
     steps:

.github/workflows/release_docker_after_publish.yml

@@ -46,7 +46,7 @@ jobs:
   notify:
     name: Notify Lark via webhook
     needs: release
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     if: ${{ always() }}
     steps:
       - uses: actions/checkout@v2

.github/workflows/release_nightly_on_schedule.yml

@@ -9,7 +9,7 @@ jobs:
   publish:
     if: github.repository == 'hpcaitech/ColossalAI'
     name: Build and publish Python 🐍 distributions 📦 to PyPI
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     timeout-minutes: 20
     outputs:
       status: ${{ steps.publish.outcome }}
@@ -36,7 +36,7 @@ jobs:
   notify:
     name: Notify Lark via webhook
     needs: publish
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     if: ${{ always() }} && github.repository == 'hpcaitech/ColossalAI'
     steps:
       - uses: actions/checkout@v2

.github/workflows/release_pypi_after_merge.yml

@@ -12,7 +12,7 @@ jobs:
   build-n-publish:
     if: github.event_name == 'workflow_dispatch' || github.repository == 'hpcaitech/ColossalAI' && github.event.pull_request.merged == true && github.base_ref == 'main'
     name: Build and publish Python 🐍 distributions 📦 to PyPI
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     timeout-minutes: 20
     steps:
     - uses: actions/checkout@v2
@@ -35,7 +35,7 @@ jobs:
   notify:
     name: Notify Lark via webhook
     needs: build-n-publish
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     if: ${{ always() }}
     steps:
       - uses: actions/checkout@v2

.github/workflows/release_test_pypi_before_merge.yml

@@ -9,7 +9,7 @@ jobs:
   build-n-publish:
     if: github.event_name == 'workflow_dispatch' || github.repository == 'hpcaitech/ColossalAI'
     name: Build and publish Python 🐍 distributions 📦 to Test PyPI
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, ubuntu-latest]-latest
     timeout-minutes: 20
     steps:
     - uses: actions/checkout@v2

.github/workflows/report_leaderboard_to_lark.yml

@@ -10,7 +10,7 @@ jobs:
   generate-and-publish:
     if: github.repository == 'hpcaitech/ColossalAI'
     name: Generate leaderboard report and publish to Lark
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     timeout-minutes: 20
     steps:
     - uses: actions/checkout@v2

.github/workflows/report_test_coverage.yml

@@ -8,7 +8,7 @@ on:
 
 jobs:
   report-test-coverage:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     if: ${{ github.event.workflow_run.conclusion == 'success' }}
     steps:
       - name: "Download artifact"

.github/workflows/run_chatgpt_examples.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/scratch/examples-data --shm-size=10.24gb
     timeout-minutes: 60
     defaults:

.github/workflows/run_chatgpt_unit_tests.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/scratch/examples-data
     timeout-minutes: 30
     defaults:

.github/workflows/run_colossalqa_unit_tests.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
+      image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0
       volumes:
         - /data/scratch/test_data_colossalqa:/data/scratch/test_data_colossalqa
         - /data/scratch/llama-tiny:/data/scratch/llama-tiny

.github/workflows/submodule.yml

@@ -7,7 +7,7 @@ on:
 
 jobs:
   sync-submodule:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     if: github.repository == 'hpcaitech/ColossalAI'
     steps:
       - name: Checkout

.github/workflows/translate_comment.yml

@@ -7,7 +7,7 @@ on:
 
 jobs:
   build:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-[self-hosted, ubuntu-latest]
     steps:
       - uses: usthe/issues-translate-action@v2.7
         with: