Remove examples of deprecated max CLI tools

The `max` CLI is deprecated in v24.5 and will be removed in a future
version.

MODULAR_ORIG_COMMIT_REV_ID: 46a294310d8732239c5f4c2a6141d559e3af0ab8

README.md

@@ -23,7 +23,7 @@ your experiences and chat with the team and other community members.
 
 In the [examples directory](https://github.com/modularml/max/tree/main/examples),
 you will find code examples and Jupyter notebooks that show how to run inference
-with MAX, and demos using the benchmarking and visualization tools.
+with MAX.
 
 ## Getting Started
 
@@ -60,12 +60,8 @@ that they can be customized, built upon, or learned from.
 ### Examples
 
 In addition to the end-to-end pipelines, there are many [examples](./examples/)
-that exercise various aspects of MAX, from
-[performing inference using PyTorch and ONNX models](./examples/inference/) to
-[demonstrating command-line tooling capabilities](./examples/tools/).
-
-You can follow the instructions in the README for each example,
-notebook or tool you want to run.
+that exercise various aspects of MAX. You can follow the instructions in the
+README for each example or notebook you want to run.
 
 ### Notebooks
 

examples/README.md

@@ -26,13 +26,3 @@ Stay tuned for an improved extensibility API that works on both CPUs and GPUs.
 
 Jupyter notebooks that showcase PyTorch and ONNX models being accelerated
 through MAX.
-
-## [Performance showcase](performance-showcase/)
-
-A head-to-head benchmark of inference performance for common models that
-demonstrates the advantages of running them with MAX.
-
-## [Command-line tools](tools/)
-
-MAX provides useful command-line tooling, and these examples demonstrate the
-capabilities of these tools.

examples/notebooks/gemma2b-python-onnx.ipynb

@@ -15,7 +15,7 @@
     "\n",
     "### Requirements\n",
     "\n",
-    "1. Please make sure you have installed `max` as described in our [getting started](https://docs.modular.com/engine/get-started/) guide\n",
+    "1. Please make sure you have installed `max` as described in our [getting started](https://docs.modular.com/max/get-started/) guide\n",
     "2. Valid [huggingface access token](https://huggingface.co/docs/hub/security-tokens)\n",
     "3. Gemma-2b is a gated model. Make sure you have accepted the [terms of use](https://huggingface.co/google/gemma-2b) to be able to continue\n",
     "4. **The model size is 13G**. Please make sure you have enough disk space to download the model and for the converted ONNX counterpart as we will use them later in this tutorial.\n",

examples/notebooks/mistral7b-python-onnx.ipynb

@@ -15,9 +15,9 @@
     "**Caveats:**\n",
     "\n",
     "* **The model size is 28G**. Please make sure you have enough disk space to download the model and for the converted ONNX counterpart as we will use them later in this tutorial.\n",
-    "* **The runtime memory requirment is around 65G** to be able finish the notebook and run all the cells.\n",
+    "* **The runtime memory requirement is around 65G** to be able finish the notebook and run all the cells.\n",
     "\n",
-    "First, make sure you have installed `max` as described in the [getting started](https://docs.staging.modular.com/engine/get-started/) as well as `PyTorch` and `transformers` packages"
+    "First, make sure you have installed `max` as described in the [getting started](https://docs.modular.com/max/get-started/) as well as `PyTorch` and `transformers` packages"
    ]
   },
   {

examples/notebooks/roberta-python-pytorch.ipynb

@@ -66,7 +66,7 @@
     "installed with the `modular` CLI tool.\n",
     "\n",
     "For instructions, see\n",
-    "[Get started with MAX Engine](https://docs.modular.com/engine/get-started)."
+    "[Get started with MAX Engine](https://docs.modular.com/max/get-started)."
    ]
   },
   {
@@ -357,9 +357,11 @@
    "source": [
     "Ta-da! 🎉\n",
     "\n",
-    "If you're running this notebook yourself, beware that this notebook does not illustrate MAX Engine's runtime performance. For actual benchmark results, try [our benchmark tool](https://docs.modular.com/engine/benchmark) or check out our [performance dashboard](https://performance.modular.com).\n",
+    "If you're running this notebook yourself, beware that this notebook does not\n",
+    "illustrate MAX Engine's runtime performance. For actual benchmark results,\n",
+    "check out our [performance dashboard](https://performance.modular.com).\n",
     "\n",
-    "For more details about the inferencing API, see the [Python API reference](https://docs.modular.com/engine/reference/python/engine)."
+    "For more details about the inferencing API, see the [Python API reference](https://docs.modular.com/max/api/python/engine)."
    ]
   }
  ],