From 86075748fe2145ea9633d5461c2d7c6e28107f29 Mon Sep 17 00:00:00 2001
From: Logan Adams <loadams@microsoft.com>
Date: Fri, 26 Jan 2024 12:53:55 -0800
Subject: [PATCH 1/4] Update checkout action to latest

---
 .github/workflows/amd-mi200.yml             | 2 +-
 .github/workflows/cpu-inference.yml         | 2 +-
 .github/workflows/formatting.yml            | 2 +-
 .github/workflows/nv-a6000.yml              | 2 +-
 .github/workflows/nv-accelerate-v100.yml    | 2 +-
 .github/workflows/nv-ds-chat.yml            | 2 +-
 .github/workflows/nv-h100.yml               | 2 +-
 .github/workflows/nv-inference.yml          | 2 +-
 .github/workflows/nv-lightning-v100.yml     | 2 +-
 .github/workflows/nv-megatron.yml           | 2 +-
 .github/workflows/nv-mii.yml                | 2 +-
 .github/workflows/nv-nightly.yml            | 2 +-
 .github/workflows/nv-pre-compile-ops.yml    | 2 +-
 .github/workflows/nv-sd.yml                 | 2 +-
 .github/workflows/nv-torch-latest-cpu.yml   | 2 +-
 .github/workflows/nv-torch-latest-v100.yml  | 2 +-
 .github/workflows/nv-torch-nightly-v100.yml | 2 +-
 .github/workflows/nv-torch110-p40.yml       | 2 +-
 .github/workflows/nv-torch110-v100.yml      | 2 +-
 .github/workflows/nv-transformers-v100.yml  | 2 +-
 .github/workflows/python.yml                | 2 +-
 .github/workflows/release.yml               | 2 +-
 22 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/.github/workflows/amd-mi200.yml b/.github/workflows/amd-mi200.yml
index e4b938d8e078..00ff72ac8929 100644
--- a/.github/workflows/amd-mi200.yml
+++ b/.github/workflows/amd-mi200.yml
@@ -21,7 +21,7 @@ jobs:
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
       # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/cpu-inference.yml b/.github/workflows/cpu-inference.yml
index 90add351f3ec..d0c3f6d8235e 100644
--- a/.github/workflows/cpu-inference.yml
+++ b/.github/workflows/cpu-inference.yml
@@ -25,7 +25,7 @@ jobs:
     runs-on: [self-hosted, cpu]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/formatting.yml b/.github/workflows/formatting.yml
index 88dfa34a0a2b..d2554b7c0038 100644
--- a/.github/workflows/formatting.yml
+++ b/.github/workflows/formatting.yml
@@ -21,7 +21,7 @@ jobs:
     runs-on: ubuntu-20.04
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: environment
         run: |
diff --git a/.github/workflows/nv-a6000.yml b/.github/workflows/nv-a6000.yml
index d7db447f5d26..92332db0d115 100644
--- a/.github/workflows/nv-a6000.yml
+++ b/.github/workflows/nv-a6000.yml
@@ -29,7 +29,7 @@ jobs:
       options: --gpus all --shm-size "8G"
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Check container state
         run: |
diff --git a/.github/workflows/nv-accelerate-v100.yml b/.github/workflows/nv-accelerate-v100.yml
index ffadd5025c87..bdc7c7683cbd 100644
--- a/.github/workflows/nv-accelerate-v100.yml
+++ b/.github/workflows/nv-accelerate-v100.yml
@@ -22,7 +22,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-ds-chat.yml b/.github/workflows/nv-ds-chat.yml
index 61011a85b92c..6985f5781e2d 100644
--- a/.github/workflows/nv-ds-chat.yml
+++ b/.github/workflows/nv-ds-chat.yml
@@ -24,7 +24,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-h100.yml b/.github/workflows/nv-h100.yml
index 93f074787372..5574ce8aa634 100644
--- a/.github/workflows/nv-h100.yml
+++ b/.github/workflows/nv-h100.yml
@@ -23,7 +23,7 @@ jobs:
       options: --gpus all --shm-size "8G"
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Check container state
         run: |
diff --git a/.github/workflows/nv-inference.yml b/.github/workflows/nv-inference.yml
index 2188171bee32..a9c704b3a7f5 100644
--- a/.github/workflows/nv-inference.yml
+++ b/.github/workflows/nv-inference.yml
@@ -25,7 +25,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-lightning-v100.yml b/.github/workflows/nv-lightning-v100.yml
index 8a385fa532b9..020d23200050 100644
--- a/.github/workflows/nv-lightning-v100.yml
+++ b/.github/workflows/nv-lightning-v100.yml
@@ -22,7 +22,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu111, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-megatron.yml b/.github/workflows/nv-megatron.yml
index 4ebaacce6b55..d9b6526bac4d 100644
--- a/.github/workflows/nv-megatron.yml
+++ b/.github/workflows/nv-megatron.yml
@@ -22,7 +22,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-mii.yml b/.github/workflows/nv-mii.yml
index e542ce7464b7..d19821aecaca 100644
--- a/.github/workflows/nv-mii.yml
+++ b/.github/workflows/nv-mii.yml
@@ -24,7 +24,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-nightly.yml b/.github/workflows/nv-nightly.yml
index 16100cafe87d..b48e3ba68f6a 100644
--- a/.github/workflows/nv-nightly.yml
+++ b/.github/workflows/nv-nightly.yml
@@ -18,7 +18,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-pre-compile-ops.yml b/.github/workflows/nv-pre-compile-ops.yml
index 68f5ee40013c..b3f4c6c61824 100644
--- a/.github/workflows/nv-pre-compile-ops.yml
+++ b/.github/workflows/nv-pre-compile-ops.yml
@@ -26,7 +26,7 @@ jobs:
       image: deepspeed/gh-builder:ubuntu1804-py38-torch1131-cu116
 
     steps:
-        - uses: actions/checkout@v3
+        - uses: actions/checkout@v4
 
         - name: environment
           run: |
diff --git a/.github/workflows/nv-sd.yml b/.github/workflows/nv-sd.yml
index 0af9517c5b59..b348d5ff931f 100644
--- a/.github/workflows/nv-sd.yml
+++ b/.github/workflows/nv-sd.yml
@@ -33,7 +33,7 @@ jobs:
       options: --gpus all --shm-size "8G"
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Check container state
         run: |
diff --git a/.github/workflows/nv-torch-latest-cpu.yml b/.github/workflows/nv-torch-latest-cpu.yml
index 7923997113ed..30c67823520c 100644
--- a/.github/workflows/nv-torch-latest-cpu.yml
+++ b/.github/workflows/nv-torch-latest-cpu.yml
@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-20.04
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-torch-latest-v100.yml b/.github/workflows/nv-torch-latest-v100.yml
index de0f5fcbc863..c9d986c7f247 100644
--- a/.github/workflows/nv-torch-latest-v100.yml
+++ b/.github/workflows/nv-torch-latest-v100.yml
@@ -22,7 +22,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-torch-nightly-v100.yml b/.github/workflows/nv-torch-nightly-v100.yml
index f46c5089b241..6e22862b17f8 100644
--- a/.github/workflows/nv-torch-nightly-v100.yml
+++ b/.github/workflows/nv-torch-nightly-v100.yml
@@ -18,7 +18,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-torch110-p40.yml b/.github/workflows/nv-torch110-p40.yml
index bf026e7f98fc..cb62c64b84b4 100644
--- a/.github/workflows/nv-torch110-p40.yml
+++ b/.github/workflows/nv-torch110-p40.yml
@@ -18,7 +18,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu111, p40]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-torch110-v100.yml b/.github/workflows/nv-torch110-v100.yml
index 406b43c154d8..e0b5f1ccae8d 100644
--- a/.github/workflows/nv-torch110-v100.yml
+++ b/.github/workflows/nv-torch110-v100.yml
@@ -18,7 +18,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu111, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/nv-transformers-v100.yml b/.github/workflows/nv-transformers-v100.yml
index 4fbc42abec5f..961c26273588 100644
--- a/.github/workflows/nv-transformers-v100.yml
+++ b/.github/workflows/nv-transformers-v100.yml
@@ -21,7 +21,7 @@ jobs:
     runs-on: [self-hosted, nvidia, cu116, v100]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - id: setup-venv
         uses: ./.github/workflows/setup-venv
diff --git a/.github/workflows/python.yml b/.github/workflows/python.yml
index 6883de4885c6..730097c50402 100644
--- a/.github/workflows/python.yml
+++ b/.github/workflows/python.yml
@@ -29,7 +29,7 @@ jobs:
       image: deepspeed/gh-builder:py${{ matrix.pyVersion }}
 
     steps:
-        - uses: actions/checkout@v3
+        - uses: actions/checkout@v4
 
         - name: environment
           run: |
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 8e016b4169cb..5a931125eff6 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -11,7 +11,7 @@ jobs:
     environment: release-env
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         ref: "master"
     - id: setup-venv

From e40ead6b36ec3f458c7d4ea638db9e4f410a9627 Mon Sep 17 00:00:00 2001
From: Logan Adams <loadams@microsoft.com>
Date: Tue, 9 Apr 2024 10:18:16 -0700
Subject: [PATCH 2/4] Update Gaudi2 workflow

---
 .github/workflows/hpu-gaudi2.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/hpu-gaudi2.yml b/.github/workflows/hpu-gaudi2.yml
index 12d8ee661fa8..a3c12d057cc9 100644
--- a/.github/workflows/hpu-gaudi2.yml
+++ b/.github/workflows/hpu-gaudi2.yml
@@ -99,7 +99,7 @@ jobs:
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
       # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Check container state
         run: |

From 3fa62e2b389233709c78021cf8cda3ea9f6fea78 Mon Sep 17 00:00:00 2001
From: Logan Adams <loadams@microsoft.com>
Date: Wed, 30 Oct 2024 07:15:56 -0700
Subject: [PATCH 3/4] Test clearing cache to help tests pass

---
 .github/workflows/nv-torch-latest-v100.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/nv-torch-latest-v100.yml b/.github/workflows/nv-torch-latest-v100.yml
index 0b8f504d8b5a..d15f41fafda9 100644
--- a/.github/workflows/nv-torch-latest-v100.yml
+++ b/.github/workflows/nv-torch-latest-v100.yml
@@ -32,6 +32,7 @@ jobs:
           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())"
+          python -c "import torch; torch.cuda.empty_cache()"
 
       - name: Install transformers
         run: |

From 12946ac11f69fc7654df3ee1bc043e71651534fe Mon Sep 17 00:00:00 2001
From: Logan Adams <loadams@microsoft.com>
Date: Wed, 30 Oct 2024 08:59:00 -0700
Subject: [PATCH 4/4] Remove clear cache

---
 .github/workflows/nv-torch-latest-v100.yml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.github/workflows/nv-torch-latest-v100.yml b/.github/workflows/nv-torch-latest-v100.yml
index d15f41fafda9..0b8f504d8b5a 100644
--- a/.github/workflows/nv-torch-latest-v100.yml
+++ b/.github/workflows/nv-torch-latest-v100.yml
@@ -32,7 +32,6 @@ jobs:
           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())"
-          python -c "import torch; torch.cuda.empty_cache()"
 
       - name: Install transformers
         run: |