PR openxla#19192: Minor documentation fixes

Imported from GitHub PR openxla#19192

This PR:
- updates broken links in the README, and overview and contribution-related docs
- removes mention of the mlperf submission from 2020
- re-formats a couple of code cells (more information inline)

Copybara import of the project:

--
3aea33a by Pavithra Eswaramoorthy <[email protected]>:

Minor docs updates for releavnce and accuracy

Signed-off-by: Pavithra Eswaramoorthy <[email protected]>

Merging this change closes openxla#19192

COPYBARA_INTEGRATE_REVIEW=openxla#19192 from pavithraes:documentation-updates ad0fb42
PiperOrigin-RevId: 694691283

Author: pavithraes

README.md

@@ -28,8 +28,9 @@ frontends and hardware backends.
 
 ## Contribute
 
-If you'd like to contribute to XLA, review [How to Contribute](CONTRIBUTING.md)
-and then see the [developer guide](docs/developer_guide.md).
+If you'd like to contribute to XLA, review
+[How to Contribute](docs/contributing.md) and then see the
+[developer guide](docs/developer_guide.md).
 
 ## Contacts
 
@@ -44,4 +45,3 @@ and then see the [developer guide](docs/developer_guide.md).
 While under TensorFlow governance, all community spaces for SIG OpenXLA are
 subject to the
 [TensorFlow Code of Conduct](https://github.com/tensorflow/tensorflow/blob/master/CODE_OF_CONDUCT.md).
-

docs/build_from_source.md

@@ -2,8 +2,8 @@
 
 This document describes how to build XLA components.
 
-If you did not clone the XLA repository or install Bazel, please check out the
-"Get started" section of the README document.
+If you did not clone the XLA repository or install Bazel, check out the initial
+sections of the [XLA Developer Guide](developer_guide.md).
 
 ## Linux
 
@@ -66,7 +66,7 @@ docker exec xla_gpu bazel build --test_output=all --spawn_strategy=sandboxed //x
 ```
 
 For more details regarding
-[TensorFlow's GPU docker images you can check out this document.](https://www.tensorflow.org/install/source#gpu_support_3)
+[TensorFlow's GPU docker images you can check out this document.](https://www.tensorflow.org/install/source#gpu_support_2)
 
 You can build XLA targets with GPU support without Docker as well. Configure and
 build targets using the following commands:
@@ -78,4 +78,4 @@ bazel build --test_output=all --spawn_strategy=sandboxed //xla/...
 ```
 
 For more details regarding
-[hermetic CUDA you can check out this document.](docs/hermetic_cuda.md)
+[hermetic CUDA you can check out this document.](hermetic_cuda.md)

docs/developer_guide.md

@@ -4,7 +4,7 @@ This guide shows you how to get started developing the XLA project.
 
 Before you begin, complete the following prerequisites:
 
-1.  Go to [CONTRIBUTING.md](../CONTRIBUTING.md) and review the contribution
+1.  Go to [Contributing page](contributing.md) and review the contribution
     process.
 2.  If you haven't already done so, sign the
     [Contributor License Agreement](https://cla.developers.google.com/about).
@@ -19,14 +19,20 @@ the repository, and create a pull request.
 
 1.  Create a fork of the [XLA repository](https://github.com/openxla/xla).
 2.  Clone your fork of the repo, replacing `<USER>` with your GitHub username:
-    ```sh
-    git clone https://github.com/<USER>/xla.git
-    ```
+    <pre class="devsite-click-to-copy">
+        <code class="devsite-terminal">
+            git clone https://github.com/<USER>/xla.git
+        </code>
+    </pre>
+
 3.  Change into the `xla` directory: `cd xla`
+
 4.  Configure the remote upstream repo:
-    ```sh
-    git remote add upstream https://github.com/openxla/xla.git
-    ```
+    <pre class="devsite-click-to-copy">
+        <code class="devsite-terminal">
+            git remote add upstream https://github.com/openxla/xla.git
+        </code>
+    </pre>
 
 ## Set up an environment
 

docs/index.md

@@ -4,10 +4,6 @@ XLA (Accelerated Linear Algebra) is an open-source compiler for machine
 learning. The XLA compiler takes models from popular frameworks such as PyTorch,
 TensorFlow, and JAX, and optimizes the models for high-performance execution
 across different hardware platforms including GPUs, CPUs, and ML accelerators.
-For example, in a
-[BERT MLPerf submission](https://blog.tensorflow.org/2020/07/tensorflow-2-mlperf-submissions.html),
-using XLA with 8 Volta V100 GPUs achieved a ~7x performance improvement and ~5x
-batch-size improvement compared to the same GPUs without XLA.
 
 As a part of the OpenXLA project, XLA is built collaboratively by
 industry-leading ML hardware and software companies, including