Use HF_TOKEN env var in CI (#7993)

.github/workflows/benchmark.yml

@@ -39,7 +39,7 @@ jobs:
           python utils/print_env.py
       - name: Diffusers Benchmarking
         env:
-            HUGGING_FACE_HUB_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
+            HF_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
             BASE_PATH: benchmark_outputs
         run: |
           export TOTAL_GPU_MEMORY=$(python -c "import torch; print(torch.cuda.get_device_properties(0).total_memory / (1024**3))")

.github/workflows/nightly_tests.yml

@@ -81,7 +81,7 @@ jobs:
 
       - name: Nightly PyTorch CUDA checkpoint (pipelines) tests
         env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -141,7 +141,7 @@ jobs:
     - name: Run nightly PyTorch CUDA tests for non-pipeline modules
       if: ${{ matrix.module != 'examples'}}
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -154,7 +154,7 @@ jobs:
     - name: Run nightly example tests with Torch
       if: ${{ matrix.module == 'examples' }}
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -211,7 +211,7 @@ jobs:
 
     - name: Run nightly LoRA tests with PEFT and Torch
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -269,7 +269,7 @@ jobs:
 
     - name: Run nightly Flax TPU tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -324,7 +324,7 @@ jobs:
 
     - name: Run nightly ONNXRuntime CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -390,7 +390,7 @@ jobs:
         shell: arch -arch arm64 bash {0}
         env:
           HF_HOME: /System/Volumes/Data/mnt/cache
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
         run: |
           ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
             --report-log=tests_torch_mps.log \

.github/workflows/push_tests.yml

@@ -87,7 +87,7 @@ jobs:
           python utils/print_env.py
       - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -144,7 +144,7 @@ jobs:
 
     - name: Run slow PyTorch CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -194,7 +194,7 @@ jobs:
 
     - name: Run slow PEFT CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -243,7 +243,7 @@ jobs:
 
     - name: Run slow Flax TPU tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -290,7 +290,7 @@ jobs:
 
     - name: Run slow ONNXRuntime CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -337,7 +337,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
@@ -378,7 +378,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -423,7 +423,7 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install timm

.github/workflows/push_tests_mps.yml

@@ -59,7 +59,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       env:
         HF_HOME: /System/Volumes/Data/mnt/cache
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
 

.github/workflows/update_metadata.yml

@@ -25,6 +25,6 @@ jobs:
 
       - name: Update metadata
         env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
         run: |
           python utils/update_metadata.py --commit_sha ${{ github.sha }}