Fix merge conflicts

.github/workflows/amd-mi200.yml

@@ -32,7 +32,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/rocm5.6
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/rocm6.0
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 

.github/workflows/cpu-torch-latest.yml

@@ -19,7 +19,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     steps:
       - uses: actions/checkout@v4
@@ -50,5 +50,5 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.3"
-          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.3"
+          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.5"
+          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.5"

.github/workflows/formatting.yml

@@ -18,7 +18,7 @@ jobs:
 
   # formatting and basic install on cpu-only machine
   unit-tests:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/hpu-gaudi2.yml

@@ -39,13 +39,14 @@ jobs:
     # The type of runner that the job will run on
     runs-on: [self-hosted, intel, gaudi2]
     container:
-      image: vault.habana.ai/gaudi-docker/1.15.1/ubuntu22.04/habanalabs/pytorch-installer-2.2.0:latest
+      image: vault.habana.ai/gaudi-docker/1.17.1/ubuntu22.04/habanalabs/pytorch-installer-2.3.1:latest
       ports:
         - 80
       options: --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice
 
     env:
       PT_HPU_LAZY_MODE: 0
+      TORCHINDUCTOR_COMPILE_THREADS: 1
       TEST_LIST: |
         test_accelerator.py
         test_autotuning.py
@@ -67,7 +68,6 @@ jobs:
         (test_flops_profiler.py and test_flops_profiler_in_inference)
         test_get_optim_files.py
         test_groups.py
-        test_init_on_device.py
         test_partition_balanced.py
         (test_adamw.py and TestAdamConfigs)
         test_coalesced_collectives.py
@@ -103,7 +103,7 @@ jobs:
       - name: Check container state
         run: |
           ldd --version
-          hl-smi
+          hl-smi -L
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 
@@ -128,7 +128,7 @@ jobs:
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
           export PT_HPU_LAZY_MODE=${PT_HPU_LAZY_MODE}
+          export TORCHINDUCTOR_COMPILE_THREADS=${TORCHINDUCTOR_COMPILE_THREADS}
           TEST_LIST=$(echo "$TEST_LIST" | awk 'NF{printf "%s%s", (NR>1 ? " or " : ""), $0} END{if (NR>1) print ""}')
           echo "TEST_LIST ${TEST_LIST}"
-          echo "PT_HPU_LAZY_MODE ${PT_HPU_LAZY_MODE}"
           pytest --verbose unit/ -k "${TEST_LIST}"

.github/workflows/no-torch.yml

@@ -0,0 +1,46 @@
+name: no-torch
+
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - '.github/workflows/no-torch.yml'
+      - 'op_builder/**'
+  schedule:
+    - cron: "0 0 * * *"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+    contents: read
+    issues: write
+
+jobs:
+  unit-tests:
+    runs-on: ubuntu-22.04
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - id: setup-venv
+        uses: ./.github/workflows/setup-venv
+
+      - name: Python environment
+        run: |
+          pip uninstall torch --yes
+          pip list
+
+      - name: Build deepspeed
+        run: |
+          DS_BUILD_STRING=" " python setup.py sdist
+
+      - name: Open GitHub issue if nightly CI fails
+        if: ${{ failure() && (github.event_name == 'schedule') }}
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true

.github/workflows/nv-a6000.yml

@@ -47,7 +47,8 @@ jobs:
       - name: Install deepspeed
         run: |
           python -m pip install docutils==0.18.1 jinja2==3.0 urllib3==1.26.11 ninja
-          python -m pip install pydantic==1.10.11
+          # Update packages included in the container that do not support pydantic 2+ to versions that do
+          python -m pip install thinc spacy confection --upgrade
           python -m pip install .[dev,1bit,autotuning,inf]
           ds_report
       - name: Python environment

.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())"
 

.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())"
 

.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

.github/workflows/nv-lightning-v100.yml

@@ -19,9 +19,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: [self-hosted, nvidia, cu111, v100]
-
-    env: {ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true} # Allow using Node16 actions
+    runs-on: [self-hosted, nvidia, cu121, v100]
 
     steps:
       - uses: actions/checkout@v3
@@ -31,7 +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())"
 

.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 --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())"
 
@@ -46,7 +46,7 @@ jobs:
           git clone https://github.com/huggingface/transformers
           cd transformers
           # if needed switch to the last known good SHA until transformers@master is fixed
-          git checkout bdf36dc
+          git checkout v4.42.4
           git rev-parse --short HEAD
           pip install .
 

.github/workflows/nv-nightly.yml

@@ -2,6 +2,9 @@ name: nv-nightly
 
 on:
   workflow_dispatch:
+  pull_request:
+    paths:
+      - '.github/workflows/nv-nightly.yml'
   schedule:
     - cron: "0 0 * * *"
 
@@ -15,7 +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
@@ -25,7 +28,7 @@ jobs:
 
       - name: Install pytorch
         run: |
-          pip install -U --cache-dir $TORCH_CACHE torch==1.13.1 torchvision --index-url https://download.pytorch.org/whl/cu117
+          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())"
 
@@ -34,7 +37,7 @@ jobs:
           git clone https://github.com/huggingface/transformers
           cd transformers
           # if needed switch to the last known good SHA until transformers@master is fixed
-          # git checkout 1cc453d33
+          git checkout v4.42.4
           git rev-parse --short HEAD
           pip install .
 
@@ -55,7 +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="1.13" --cuda_ver="11.7"
+          pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="2.5" --cuda_ver="12.1"
 
       - name: Open GitHub issue if nightly CI fails
         if: ${{ failure() && (github.event_name == 'schedule') }}

.github/workflows/nv-pre-compile-ops.yml

@@ -21,7 +21,7 @@ concurrency:
 
 jobs:
   unit-tests:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     container:
       image: deepspeed/gh-builder:ubuntu1804-py38-torch1131-cu116
 
@@ -36,7 +36,7 @@ jobs:
             #python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
         - name: Compile DeepSpeed Ops
           run: |
-            DS_ACCELERATOR=cuda DS_ENABLE_NINJA=1 TORCH_CUDA_ARCH_LIST="7.0;7.5;8.0" DS_BUILD_OPS=1 DS_BUILD_SPARSE_ATTN=0 DS_BUILD_FP_QUANTIZER=0 DS_BUILD_CUTLASS_OPS=0 DS_BUILD_RAGGED_DEVICE_OPS=0 DS_BUILD_EVOFORMER_ATTN=0 pip3 install .
+            DS_ACCELERATOR=cuda DS_ENABLE_NINJA=1 TORCH_CUDA_ARCH_LIST="7.0;7.5;8.0" DS_BUILD_OPS=1 DS_BUILD_SPARSE_ATTN=0 DS_BUILD_FP_QUANTIZER=0 DS_BUILD_CUTLASS_OPS=0 DS_BUILD_GDS=0 DS_BUILD_RAGGED_DEVICE_OPS=0 DS_BUILD_EVOFORMER_ATTN=0 pip3 install .
         - name: DS Report
           run: |
              ds_report

.github/workflows/nv-sd.yml

@@ -53,6 +53,8 @@ jobs:
           pip install image-similarity-measures
           python -m pip install opencv-python==4.6.* --force-reinstall
           python -m pip install docutils==0.18.1 jinja2==3.0 urllib3==1.26.11 ninja
+          # Update packages included in the container that do not support pydantic 2+ to versions that do
+          python -m pip install thinc spacy confection --upgrade
           python -m pip install .[dev,1bit,autotuning,sd]
           ds_report
       - name: Python environment

.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="2.3" --cuda_ver="11.8"
-          pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.3" --cuda_ver="11.8"
+          pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="2.5" --cuda_ver="12.1"
+          pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.5" --cuda_ver="12.1"

.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())"
 

.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())"
 

.github/workflows/python.yml

@@ -24,7 +24,7 @@ jobs:
         pyVersion: ["3.7", "3.8", "3.9", "3.10"]
       fail-fast: false
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     container:
       image: deepspeed/gh-builder:py${{ matrix.pyVersion }}
 

.github/workflows/release.yml

@@ -7,7 +7,7 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     environment: release-env
 
     steps: