Remove Support For Deprecated Habana (#21327)

* remove habana

* changelog

* remove from install

* update docs

* update

* update

* pytest match

Author: justusschock

.github/workflows/ci-tests-pytorch.yml

@@ -129,8 +129,8 @@ jobs:
         run: |
           uv pip install ".[${EXTRA_PREFIX}extra,${EXTRA_PREFIX}test,${EXTRA_PREFIX}strategies]" \
             --upgrade \
-            -r requirements/_integrations/accelerators.txt \
-            --find-links="${TORCH_URL}"
+            --find-links="${TORCH_URL}" \
+            --find-links="https://download.pytorch.org/whl/torch-tensorrt"
           uv pip list
 
       - name: Drop LAI from extensions

docs/source-pytorch/common/index.rst

@@ -16,7 +16,6 @@
    Save memory with half-precision <precision>
    ../advanced/model_parallel
    Train on single or multiple GPUs <../accelerators/gpu>
-   Train on single or multiple HPUs <../integrations/hpu/index>
    Train on single or multiple TPUs <../accelerators/tpu>
    Train on MPS <../accelerators/mps>
    Use a pretrained model <../advanced/pretrained>
@@ -161,13 +160,6 @@ How-to Guides
     :col_css: col-md-4
     :height: 180
 
-.. displayitem::
-    :header: Train on single or multiple HPUs
-    :description: Train models faster with HPU accelerators
-    :button_link: ../integrations/hpu/index.html
-    :col_css: col-md-4
-    :height: 180
-
 .. displayitem::
     :header: Train on single or multiple TPUs
     :description: TTrain models faster with TPU accelerators

docs/source-pytorch/common_usecases.rst

@@ -126,13 +126,6 @@ Customize and extend Lightning for things like custom hardware or distributed st
    :button_link: accelerators/gpu.html
    :height: 100
 
-.. displayitem::
-   :header: Train on single or multiple HPUs
-   :description: Train models faster with HPUs.
-   :col_css: col-md-12
-   :button_link: integrations/hpu/index.html
-   :height: 100
-
 .. displayitem::
    :header: Train on single or multiple TPUs
    :description: Train models faster with TPUs.

docs/source-pytorch/conf.py

@@ -86,20 +86,6 @@ def _load_py_module(name: str, location: str) -> ModuleType:
     os.path.join(_PATH_HERE, _FOLDER_GENERATED, "CHANGELOG.md"),
 )
 
-# Copy Accelerator docs
-assist_local.AssistantCLI.pull_docs_files(
-    gh_user_repo="Lightning-AI/lightning-Habana",
-    target_dir="docs/source-pytorch/integrations/hpu",
-    # checkout="refs/tags/1.6.0",
-    checkout="5549fa927d5501d31aac0c9b2ed479be62a02cbc",
-)
-# the HPU also need some images
-URL_RAW_DOCS_HABANA = "https://raw.githubusercontent.com/Lightning-AI/lightning-Habana/1.5.0/docs/source"
-for img in ["_images/HPUProfiler.png", "_images/IGP.png"]:
-    img_ = os.path.join(_PATH_HERE, "integrations", "hpu", img)
-    os.makedirs(os.path.dirname(img_), exist_ok=True)
-    urllib.request.urlretrieve(f"{URL_RAW_DOCS_HABANA}/{img}", img_)
-
 # Copy strategies docs as single pages
 assist_local.AssistantCLI.pull_docs_files(
     gh_user_repo="Lightning-Universe/lightning-Hivemind",
@@ -360,7 +346,6 @@ def _load_py_module(name: str, location: str) -> ModuleType:
     "numpy": ("https://numpy.org/doc/stable/", None),
     "PIL": ("https://pillow.readthedocs.io/en/stable/", None),
     "torchmetrics": ("https://lightning.ai/docs/torchmetrics/stable/", None),
-    "lightning_habana": ("https://lightning-ai.github.io/lightning-Habana/", None),
     "tensorboardX": ("https://tensorboardx.readthedocs.io/en/stable/", None),
     # needed for referencing Fabric from lightning scope
     "lightning.fabric": ("https://lightning.ai/docs/fabric/stable/", None),
@@ -467,10 +452,6 @@ def _load_py_module(name: str, location: str) -> ModuleType:
     ("py:class", "lightning.pytorch.utilities.types.LRSchedulerConfigType"),
     ("py:class", "lightning.pytorch.utilities.types.OptimizerConfig"),
     ("py:class", "lightning.pytorch.utilities.types.OptimizerLRSchedulerConfig"),
-    ("py:class", "lightning_habana.pytorch.plugins.precision.HPUPrecisionPlugin"),
-    ("py:class", "lightning_habana.pytorch.strategies.HPUDDPStrategy"),
-    ("py:class", "lightning_habana.pytorch.strategies.HPUParallelStrategy"),
-    ("py:class", "lightning_habana.pytorch.strategies.SingleHPUStrategy"),
     ("py:obj", "logger.experiment"),
     ("py:class", "mlflow.tracking.MlflowClient"),
     ("py:attr", "model"),
@@ -646,7 +627,7 @@ def package_list_from_file(file):
     r"starter/installation.html$",
     r"^../common/trainer.html#trainer-flags$",
     "https://deepgenerativemodels.github.io/assets/slides/cs236_lecture11.pdf",
-    "https://developer.habana.ai", # returns 403 error but redirects to intel.com documentation
+    "https://www.supermicro.com", # returns 403 error
     "https://www.intel.com/content/www/us/en/products/docs/processors/what-is-a-gpu.html",
     "https://www.microsoft.com/en-us/research/blog/zero-infinity-and-deepspeed-unlocking-unprecedented-model-scale-for-deep-learning-training/",  # noqa: E501
     "https://stackoverflow.com/questions/66640705/how-can-i-install-grpcio-on-an-apple-m1-silicon-laptop",

docs/source-pytorch/expertise_levels.rst

@@ -190,23 +190,15 @@ Configure all aspects of Lightning for advanced usecases.
    :tag: advanced
 
 .. displayitem::
-   :header: Level 18: Explore HPUs
-   :description: Explore Havana Gaudi Processing Unit (HPU) for model scaling.
-   :col_css: col-md-6
-   :button_link: levels/advanced_level_19.html
-   :height: 150
-   :tag: advanced
-
-.. displayitem::
-   :header: Level 19: Master TPUs
+   :header: Level 18: Master TPUs
    :description: Master TPUs and run on cloud TPUs.
    :col_css: col-md-6
    :button_link: levels/advanced_level_20.html
    :height: 150
    :tag: advanced
 
 .. displayitem::
-   :header: Level 20: Train models with billions of parameters
+   :header: Level 19: Train models with billions of parameters
    :description: Scale GPU training to models with billions of parameters
    :col_css: col-md-6
    :button_link: levels/advanced_level_21.html

docs/source-pytorch/extensions/accelerator.rst

@@ -10,7 +10,6 @@ Currently there are accelerators for:
 - CPU
 - :doc:`GPU <../accelerators/gpu>`
 - :doc:`TPU <../accelerators/tpu>`
-- :doc:`HPU <../integrations/hpu/index>`
 - :doc:`MPS <../accelerators/mps>`
 
 The Accelerator is part of the Strategy which manages communication across multiple devices (distributed communication).

docs/source-pytorch/extensions/strategy.rst

@@ -78,12 +78,6 @@ The below table lists all relevant strategies available in Lightning with their
    * - deepspeed
      - :class:`~lightning.pytorch.strategies.DeepSpeedStrategy`
      - Provides capabilities to run training using the DeepSpeed library, with training optimizations for large billion parameter models. :doc:`Learn more. <../advanced/model_parallel/deepspeed>`
-   * - hpu_parallel
-     - ``HPUParallelStrategy``
-     - Strategy for distributed training on multiple HPU devices. :doc:`Learn more. <../integrations/hpu/index>`
-   * - hpu_single
-     - ``SingleHPUStrategy``
-     - Strategy for training on a single HPU device. :doc:`Learn more. <../integrations/hpu/index>`
    * - xla
      - :class:`~lightning.pytorch.strategies.XLAStrategy`
      - Strategy for training on multiple TPU devices using the :func:`torch_xla.distributed.xla_multiprocessing.spawn` method. :doc:`Learn more. <../accelerators/tpu>`

docs/source-pytorch/glossary/index.rst

@@ -21,7 +21,6 @@
    GPU <../accelerators/gpu>
    Half precision <../common/precision>
    Hooks <../common/hooks>
-   HPU <../integrations/hpu/index>
    Inference <../deploy/production_intermediate>
    Lightning CLI <../cli/lightning_cli>
    LightningDataModule <../data/datamodule>
@@ -187,13 +186,6 @@ Glossary
    :button_link: ../common/hooks.html
    :height: 100
 
-.. displayitem::
-   :header: HPU
-   :description: Habana Gaudi AI Processor Unit for faster training
-   :col_css: col-md-12
-   :button_link: ../integrations/hpu/index.html
-   :height: 100
-
 .. displayitem::
    :header: Inference
    :description: Making predictions by applying a trained model to unlabeled examples

docs/source-pytorch/integrations/hpu/index.rst

@@ -46,23 +46,15 @@ Configure all aspects of Lightning for advanced usecases.
    :tag: advanced
 
 .. displayitem::
-   :header: Level 18: Explore HPUs
-   :description: Explore Habana Gaudi Processing Unit (HPU) for model scaling.
-   :col_css: col-md-6
-   :button_link: advanced_level_19.html
-   :height: 150
-   :tag: advanced
-
-.. displayitem::
-   :header: Level 19: Master TPUs
+   :header: Level 18: Master TPUs
    :description: Master TPUs and run on cloud TPUs.
    :col_css: col-md-6
    :button_link: advanced_level_20.html
    :height: 150
    :tag: advanced
 
 .. displayitem::
-   :header: Level 20: Train models with billions of parameters
+   :header: Level 19: Train models with billions of parameters
    :description: Scale GPU training to models with billions of parameters
    :col_css: col-md-6
    :button_link: advanced_level_21.html