Update workflows that use cuda 12.1 to use runners with 12.4

deepspeedai · Feb 4, 2025 · 357fced · 357fced
1 parent 241bffd
commit 357fced
Show file tree

Hide file tree

Showing 9 changed files with 18 additions and 18 deletions.
diff --git a/.github/workflows/nv-accelerate-v100.yml b/.github/workflows/nv-accelerate-v100.yml
@@ -19,7 +19,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -29,7 +29,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-ds-chat.yml b/.github/workflows/nv-ds-chat.yml
@@ -27,7 +27,7 @@ permissions:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -37,7 +37,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-inference.yml b/.github/workflows/nv-inference.yml
@@ -22,7 +22,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -32,7 +32,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-lightning-v100.yml b/.github/workflows/nv-lightning-v100.yml
@@ -19,7 +19,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -29,7 +29,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-mii.yml b/.github/workflows/nv-mii.yml
@@ -27,7 +27,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -37,7 +37,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
+          pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-nightly.yml b/.github/workflows/nv-nightly.yml
@@ -18,7 +18,7 @@ permissions:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -28,7 +28,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-torch-latest-v100.yml b/.github/workflows/nv-torch-latest-v100.yml
@@ -19,7 +19,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -29,7 +29,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-torch-nightly-v100.yml b/.github/workflows/nv-torch-nightly-v100.yml
@@ -18,7 +18,7 @@ permissions:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -28,7 +28,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu121
+          pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

diff --git a/.github/workflows/nv-transformers-v100.yml b/.github/workflows/nv-transformers-v100.yml
@@ -18,7 +18,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu121, v100]
+    runs-on: [self-hosted, nvidia, cu124, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -29,7 +29,7 @@ jobs:
       - name: Install pytorch
         run: |
           # use the same pytorch version as transformers CI
-          pip install -U --cache-dir $TORCH_CACHE torch==2.0.1+cu121 --index-url https://download.pytorch.org/whl/cu121
+          pip install -U --cache-dir $TORCH_CACHE torch==2.0.1+cu124 --index-url https://download.pytorch.org/whl/cu124
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"