Merge branch 'master' into fix_bwd_memcpy_4_infinity

microsoft · Oct 29, 2024 · 1fd255e · 1fd255e
2 parents 109bb6d + 07cac9e
commit 1fd255e
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 12 deletions.
diff --git a/.github/workflows/hpu-gaudi2.yml b/.github/workflows/hpu-gaudi2.yml
@@ -39,7 +39,7 @@ jobs:
     # The type of runner that the job will run on
     runs-on: [self-hosted, intel, gaudi2]
     container:
-      image: vault.habana.ai/gaudi-docker/1.17.0/ubuntu22.04/habanalabs/pytorch-installer-2.3.1:latest
+      image: vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
       ports:
         - 80
       options: --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice

diff --git a/.github/workflows/nv-a6000.yml b/.github/workflows/nv-a6000.yml
@@ -23,7 +23,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:23.03-py3
+      image: nvcr.io/nvidia/pytorch:24.03-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -47,8 +47,6 @@ jobs:
       - name: Install deepspeed
         run: |
           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,inf]
           ds_report
       - name: Python environment
@@ -58,8 +56,8 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.0" --cuda_ver="12"
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.0" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.3" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.3" --cuda_ver="12"
       - name: MII unit tests
         run: |
           BRANCH="main"

diff --git a/.github/workflows/nv-human-eval.yml b/.github/workflows/nv-human-eval.yml
@@ -11,7 +11,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:23.03-py3
+      image: nvcr.io/nvidia/pytorch:24.03-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -50,4 +50,4 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.0" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.3" --cuda_ver="12"
diff --git a/.github/workflows/nv-sd.yml b/.github/workflows/nv-sd.yml
@@ -27,7 +27,7 @@ jobs:
   sd-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:23.03-py3
+      image: nvcr.io/nvidia/pytorch:24.03-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -53,8 +53,6 @@ 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
@@ -64,7 +62,7 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'stable_diffusion' -k "TestStableDiffusion" unit/ --torch_ver="2.0" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'stable_diffusion' -k "TestStableDiffusion" unit/ --torch_ver="2.3" --cuda_ver="12"
 
       - name: Open GitHub issue if weekly CI fails
         if: ${{ failure() && (github.event_name == 'schedule') }}