Merge branch 'remove-conda' of github.com:pytorch/tutorials into remove-conda

Author: AlannaBurke

.ci/docker/requirements.txt

@@ -14,7 +14,7 @@ tqdm==4.66.1
 numpy==1.24.4
 matplotlib
 librosa
-torch==2.6
+torch==2.7
 torchvision
 torchdata
 networkx
@@ -67,7 +67,7 @@ iopath
 pygame==2.6.0
 pycocotools
 semilearn==0.3.2
-torchao==0.5.0
+torchao==0.10.0
 segment_anything==1.0
 torchrec==1.1.0; platform_system == "Linux"
-fbgemm-gpu==1.1.0; platform_system == "Linux"
+fbgemm-gpu==1.2.0; platform_system == "Linux"

.jenkins/build.sh

@@ -22,13 +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 pip uninstall -y torch torchvision torchaudio torchtext torchdata torchrl tensordict
 # 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 torchrl tensordict
-pip3 install torch==2.7.0 torchvision torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu126
-#sudo pip uninstall -y fbgemm-gpu
+# pip3 install torch==2.7.0 torchvision torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu126
 # Install two language tokenizers for Translation with TorchText tutorial
 python -m spacy download en_core_web_sm
 python -m spacy download de_core_news_sm

.jenkins/validate_tutorials_built.py

@@ -31,6 +31,7 @@
     "prototype_source/vmap_recipe",
     "prototype_source/torchscript_freezing",
     "prototype_source/nestedtensor",
+    "prototype_source/gpu_direct_storage", # requires specific filesystem + GPUDirect Storage to be set up
     "recipes_source/recipes/saving_and_loading_models_for_inference",
     "recipes_source/recipes/saving_multiple_models_in_one_file",
     "recipes_source/recipes/tensorboard_with_pytorch",
@@ -51,14 +52,8 @@
     "intermediate_source/text_to_speech_with_torchaudio",
     "intermediate_source/tensorboard_profiler_tutorial", # reenable after 2.0 release.
     "advanced_source/semi_structured_sparse", # reenable after 3303 is fixed.
-    "intermediate_source/mario_rl_tutorial", # reenable after 3302 is fixed
-    "intermediate_source/reinforcement_ppo", # reenable after 3302 is fixed
-    "intermediate_source/pinmem_nonblock", # reenable after 3302 is fixed
-    "intermediate_source/dqn_with_rnn_tutorial", # reenable after 3302 is fixed
-    "advanced_source/pendulum", # reenable after 3302 is fixed
-    "advanced_source/coding_ddpg", # reenable after 3302 is fixed
-    "intermediate_source/torchrec_intro_tutorial", # reenable after 3302 is fixed
-    "recipes_source/recipes/reasoning_about_shapes" # reenable after 3326 is fixed
+    "intermediate_source/torchrec_intro_tutorial", # reenable after 3302 is fixe
+    "intermediate_source/memory_format_tutorial", # causes other tutorials like torch_logs fail. "state" issue, reseting dynamo didn't help
 ]
 
 def tutorial_source_dirs() -> List[Path]:

advanced_source/sharding.rst

@@ -14,9 +14,10 @@ Requirements: - python >= 3.7
 We highly recommend CUDA when using torchRec. If using CUDA: - cuda >=
 11.0
 
+.. Should these be updated?
 .. code:: python
 
-    # install conda to make installying pytorch with cudatoolkit 11.3 easier. 
+    # install conda to make installying pytorch with cudatoolkit 11.3 easier.
     !sudo rm Miniconda3-py37_4.9.2-Linux-x86_64.sh Miniconda3-py37_4.9.2-Linux-x86_64.sh.*
     !sudo wget https://repo.anaconda.com/miniconda/Miniconda3-py37_4.9.2-Linux-x86_64.sh
     !sudo chmod +x Miniconda3-py37_4.9.2-Linux-x86_64.sh
@@ -209,7 +210,7 @@ embedding table placement using planner and generate sharded model using
         )
         sharders = [cast(ModuleSharder[torch.nn.Module], EmbeddingBagCollectionSharder())]
         plan: ShardingPlan = planner.collective_plan(module, sharders, pg)
-    
+
         sharded_model = DistributedModelParallel(
             module,
             env=ShardingEnv.from_process_group(pg),
@@ -230,7 +231,7 @@ ranks.
 .. code:: python
 
     import multiprocess
-       
+
     def spmd_sharing_simulation(
         sharding_type: ShardingType = ShardingType.TABLE_WISE,
         world_size = 2,
@@ -250,7 +251,7 @@ ranks.
           )
           p.start()
           processes.append(p)
-    
+
       for p in processes:
           p.join()
           assert 0 == p.exitcode
@@ -329,4 +330,3 @@ With data parallel, we will repeat the tables for all devices.
 
     rank:0,sharding plan: {'': {'large_table_0': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None), 'large_table_1': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None), 'small_table_0': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None), 'small_table_1': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None)}}
     rank:1,sharding plan: {'': {'large_table_0': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None), 'large_table_1': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None), 'small_table_0': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None), 'small_table_1': ParameterSharding(sharding_type='data_parallel', compute_kernel='batched_dense', ranks=[0, 1], sharding_spec=None)}}
-