Merge branch 'master' into lyj/llama

microsoft · Oct 8, 2024 · e22ceb7 · e22ceb7
2 parents 3d6c651 + 20695b3
commit e22ceb7
Show file tree

Hide file tree

Showing 9 changed files with 24 additions and 24 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, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, 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/cu118
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
           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
@@ -26,7 +26,7 @@ permissions:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -36,7 +36,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip3 install -U --cache-dir $TORCH_CACHE torch --index-url https://download.pytorch.org/whl/cu118
+          pip3 install -U --cache-dir $TORCH_CACHE torch --index-url https://download.pytorch.org/whl/cu121
           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, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, 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/cu118
+          pip install -U --cache-dir $TORCH_CACHE torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu121
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 
@@ -58,8 +58,8 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          #pytest $PYTEST_OPTS -m 'seq_inference' unit/ --torch_ver="2.1" --cuda_ver="11.8"
-          pytest $PYTEST_OPTS -m 'inference_ops' unit/ --torch_ver="2.1" --cuda_ver="11.8"
-          pytest $PYTEST_OPTS --forked -n 4 -m 'inference' unit/ --torch_ver="2.1" --cuda_ver="11.8"
+          #pytest $PYTEST_OPTS -m 'seq_inference' unit/ --torch_ver="2.1" --cuda_ver="12.1"
+          pytest $PYTEST_OPTS -m 'inference_ops' unit/ --torch_ver="2.1" --cuda_ver="12.1"
+          pytest $PYTEST_OPTS --forked -n 4 -m 'inference' unit/ --torch_ver="2.1" --cuda_ver="12.1"
           # run ds_report again to check updated op list
           ds_report
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, cu111, v100]
+    runs-on: [self-hosted, nvidia, cu121, v100]
 
     env: {ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true} # Allow using Node16 actions
 
@@ -31,7 +31,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
           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, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, 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/cu118
+          pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
           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, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, 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/cu118
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 
@@ -58,7 +58,7 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="2.4" --cuda_ver="11.8"
+          pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="2.4" --cuda_ver="12.1"
 
       - name: Open GitHub issue if nightly CI fails
         if: ${{ failure() && (github.event_name == 'schedule') }}

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, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, 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/cu118
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 
@@ -55,5 +55,5 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="2.4" --cuda_ver="11.8"
-          pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.4" --cuda_ver="11.8"
+          pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="2.4" --cuda_ver="12.1"
+          pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.4" --cuda_ver="12.1"
diff --git a/.github/workflows/nv-torch-nightly-v100.yml b/.github/workflows/nv-torch-nightly-v100.yml
@@ -15,7 +15,7 @@ permissions:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, v100]
 
     steps:
       - uses: actions/checkout@v4
@@ -25,7 +25,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu118
+          pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu121
           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, cu117, v100]
+    runs-on: [self-hosted, nvidia, cu121, 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+cu118 --index-url https://download.pytorch.org/whl/cu118
+          pip install -U --cache-dir $TORCH_CACHE torch==2.0.1+cu121 --index-url https://download.pytorch.org/whl/cu121
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"