Merge branch 'main' into remove-files-gh-pages

Author: svekars

index.rst

@@ -612,20 +612,6 @@ Welcome to PyTorch Tutorials
    :link: advanced/static_quantization_tutorial.html
    :tags: Quantization
 
-.. customcarditem::
-   :header: Grokking PyTorch Intel CPU Performance from First Principles
-   :card_description: A case study on the TorchServe inference framework optimized with Intel® Extension for PyTorch.
-   :image: _static/img/thumbnails/cropped/generic-pytorch-logo.png
-   :link: intermediate/torchserve_with_ipex
-   :tags: Model-Optimization,Production
-
-.. customcarditem::
-   :header: Grokking PyTorch Intel CPU Performance from First Principles (Part 2)
-   :card_description: A case study on the TorchServe inference framework optimized with Intel® Extension for PyTorch (Part 2).
-   :image: _static/img/thumbnails/cropped/generic-pytorch-logo.png
-   :link: intermediate/torchserve_with_ipex_2
-   :tags: Model-Optimization,Production
-
 .. customcarditem::
    :header: Multi-Objective Neural Architecture Search with Ax
    :card_description: Learn how to use Ax to search over architectures find optimal tradeoffs between accuracy and latency.
@@ -1071,8 +1057,6 @@ Additional Resources
    intermediate/dynamic_quantization_bert_tutorial
    intermediate/quantized_transfer_learning_tutorial
    advanced/static_quantization_tutorial
-   intermediate/torchserve_with_ipex
-   intermediate/torchserve_with_ipex_2
    intermediate/nvfuser_intro_tutorial
    intermediate/ax_multiobjective_nas_tutorial
    intermediate/torch_compile_tutorial

recipes_source/recipes_index.rst

@@ -450,15 +450,6 @@ Recipes are bite-sized, actionable examples of how to use specific PyTorch featu
    :link: ../recipes/distributed_comm_debug_mode.html
    :tags: Distributed-Training
 
-.. TorchServe
-
-.. customcarditem::
-   :header: Deploying a PyTorch Stable Diffusion model as a Vertex AI Endpoint
-   :card_description: Learn how to deploy model in Vertex AI with TorchServe
-   :image: ../_static/img/thumbnails/cropped/generic-pytorch-logo.png
-   :link: ../recipes/torchserve_vertexai_tutorial.html
-   :tags: Production
-
 .. End of tutorial card section
 
 .. raw:: html

recipes_source/torch_compile_caching_tutorial.rst

@@ -88,6 +88,9 @@ The aforementioned ``Mega-Cache`` is composed of individual components that can
 * ``InductorCache``: A bundle of ``FXGraphCache`` and ``Triton`` cache.
 * ``AOTAutogradCache``: A cache of joint graph artifacts.
 * ``PGO-cache``: A cache of dynamic shape decisions to reduce number of recompilations.
+* `AutotuningCache <https://github.com/pytorch/pytorch/blob/795a6a0affd349adfb4e3df298b604b74f27b44e/torch/_inductor/runtime/autotune_cache.py#L116>`__: 
+    * ``Inductor`` generates ``Triton`` kernels and benchmarks them to select the fastest kernels.
+    * ``torch.compile``'s built-in ``AutotuningCache`` caches these results.
 
 All these cache artifacts are written to ``TORCHINDUCTOR_CACHE_DIR`` which by default will look like ``/tmp/torchinductor_myusername``.