Merge branch 'main' into titaiwang/dynamo_true_api

Author: svekars

.ci/docker/requirements.txt

@@ -14,7 +14,7 @@ tqdm==4.66.1
 numpy==1.24.4
 matplotlib
 librosa
-torch==2.5
+torch==2.6
 torchvision
 torchdata
 networkx
@@ -70,4 +70,4 @@ semilearn==0.3.2
 torchao==0.5.0
 segment_anything==1.0
 torchrec==1.0.0; platform_system == "Linux"
-fbgemm-gpu==1.0.0; platform_system == "Linux"
+fbgemm-gpu==1.1.0; platform_system == "Linux"

.jenkins/build.sh

@@ -22,10 +22,10 @@ sudo apt-get install -y pandoc
 #Install PyTorch Nightly for test.
 # Nightly - pip install --pre torch torchvision torchaudio -f https://download.pytorch.org/whl/nightly/cu102/torch_nightly.html
 # Install 2.5 to merge all 2.4 PRs - uncomment to install nightly binaries (update the version as needed).
-sudo pip uninstall -y torch torchvision torchaudio torchtext torchdata
-sudo pip3 install torch==2.6.0 torchvision --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
-sudo pip uninstall -y fbgemm-gpu torchrec
-sudo pip3 install fbgemm-gpu==1.1.0 torchrec==1.0.0 --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
+# sudo pip uninstall -y torch torchvision torchaudio torchtext torchdata
+# sudo pip3 install torch==2.6.0 torchvision --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
+# sudo pip uninstall -y fbgemm-gpu torchrec
+# sudo pip3 install fbgemm-gpu==1.1.0 torchrec==1.0.0 --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
 
 # Install two language tokenizers for Translation with TorchText tutorial
 python -m spacy download en_core_web_sm

intermediate_source/transformer_building_blocks.py

@@ -3,8 +3,6 @@
 =============================================================================================================
 **Author:** `Mikayla Gawarecki <https://github.com/mikaylagawarecki>`_
 
-.. note::
-    This tutorial currently requires you to use the PyTorch nightly build.
 
 .. grid:: 2
 

recipes_source/recipes/amp_recipe.py

@@ -150,7 +150,7 @@ def make_model(in_size, out_size, num_layers):
 # The same ``GradScaler`` instance should be used for the entire convergence run.
 # If you perform multiple convergence runs in the same script, each run should use
 # a dedicated fresh ``GradScaler`` instance. ``GradScaler`` instances are lightweight.
-scaler = torch.cuda.amp.GradScaler()
+scaler = torch.amp.GradScaler("cuda")
 
 for epoch in range(0): # 0 epochs, this section is for illustration only
     for input, target in zip(data, targets):
@@ -182,7 +182,7 @@ def make_model(in_size, out_size, num_layers):
 
 net = make_model(in_size, out_size, num_layers)
 opt = torch.optim.SGD(net.parameters(), lr=0.001)
-scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
+scaler = torch.amp.GradScaler("cuda" ,enabled=use_amp)
 
 start_timer()
 for epoch in range(epochs):