Taichi removed (#5802)

(cherry picked from commit c154b7e0a3)

.readthedocs.yaml

@@ -6,7 +6,7 @@ version: 2
 sphinx:
    configuration: docs/conf.py
 
-formats: [htmlzip]
+formats: [htmlzip, pdf]
 
 python:
    install:

.wordlist.txt

@@ -45,6 +45,7 @@ Bootloader
 CAS
 CCD
 CDNA
+CGUI
 CHTML
 CIFAR
 CLI
@@ -115,6 +116,7 @@ DevCap
 DirectX
 Dockerfile
 Doxygen
+dropless
 ELMo
 ENDPGM
 EPYC
@@ -270,6 +272,7 @@ Makefiles
 Matplotlib
 Matrox
 MaxText
+Megablocks
 Megatrends
 Megatron
 Mellanox
@@ -279,6 +282,7 @@ Miniconda
 MirroredStrategy
 Mixtral
 MosaicML
+MoEs
 Mpops
 Multicore
 Multithreaded
@@ -408,6 +412,7 @@ SDMA
 SDPA
 SDRAM
 SENDMSG
+SGLang
 SGPR
 SGPRs
 SHA
@@ -863,6 +868,7 @@ seealso
 sendmsg
 seqs
 serializers
+sglang
 shader
 sharding
 sigmoid

docs/compatibility/compatibility-matrix-historical-6.0.csv

@@ -30,9 +30,10 @@ ROCm Version,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,
       :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`,2.4.0,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.2,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
 ,,,,,,,,,,,,,,,,,
       ,,,,,,,,,,,,,,,,,

docs/compatibility/compatibility-matrix.rst

@@ -56,7 +56,7 @@ compatibility and system requirements.
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.35,0.4.35,0.4.31  
       :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,85f95ae
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`,2.4.0,2.4.0,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,0.7.0
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.17.3
       ,,,
       THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
@@ -241,6 +241,9 @@ Expand for full historical view of:
    .. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
    .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
    .. [#verl_compat] verl is only supported on ROCm 6.2.0.
+   .. [#stanford-megatron-lm_compat] Stanford Megatron-LM is only supported on ROCm 6.3.0.
+   .. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
+   .. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
    .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
    .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
    

docs/compatibility/ml-compatibility/dgl-compatibility.rst

@@ -42,16 +42,16 @@ GAT, GCN and GraphSage. Using these we can support a variety of use-cases such a
 - 1D (Temporal) and 2D (Image) Classification
 - Drug Discovery
 
-Refer to :doc:`ROCm DGL blog posts <https://rocm.blogs.amd.com/blog/tag/dgl.html>` 
+Multiple use cases of DGL have been tested and verified.
-for examples and best practices to optimize your training workflows on AMD GPUs. 
+However, a recommended example follows a drug discovery pipeline using the ``SE3Transformer``.
+Refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`_, 
+where you can search for DGL examples and best practices to optimize your training workflows on AMD GPUs. 
 
 Coverage includes:
 
 - Single-GPU training/inference
 - Multi-GPU training
 
-Benchmarking details are included in the :doc:`Benchmarks` section.
-
 
 .. _dgl-docker-compat:
 
@@ -252,4 +252,4 @@ Unsupported functions
 * ``gather_mm_idx_b``
 * ``pgexplainer``
 * ``sample_labors_prob``
-* ``sample_labors_noprob``
+* ``sample_labors_noprob``

docs/compatibility/ml-compatibility/jax-compatibility.rst

@@ -97,7 +97,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
 with ROCm backends on Docker Hub. The following Docker image tags and
 associated inventories represent the latest JAX version from the official Docker Hub and are validated for
-`ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click the |docker-icon|
+`ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`_. Click the |docker-icon|
 icon to view the image on Docker Hub.
 
 .. list-table:: JAX Docker image components
@@ -110,7 +110,7 @@ icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.12/images/sha256-7a0745a2a2758bdf86397750bac00e9086cbf67d170cfdbb08af73f7c7d18a6a"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.2-jax0.4.35-py3.12/images/sha256-8918fa806a172c1a10eb2f57131eb31b5d7c8fa1656b8729fe7d3d736112de83"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
 
       - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
       - Ubuntu 24.04
@@ -118,7 +118,7 @@ icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.10/images/sha256-5f9e8d6e6e69fdc9a1a3f2ba3b1234c3f46c53b7468538c07fd18b00899da54f"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.2-jax0.4.35-py3.10/images/sha256-a394be13c67b7fc602216abee51233afd4b6cb7adaa57ca97e688fba82f9ad79"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
 
       - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
       - Ubuntu 22.04

docs/compatibility/ml-compatibility/megablocks-compatibility.rst

@@ -0,0 +1,93 @@
+:orphan:
+
+.. meta::
+    :description: Megablocks compatibility
+    :keywords: GPU, megablocks, compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Megablocks compatibility
+********************************************************************************
+
+Megablocks is a light-weight library for mixture-of-experts (MoE) training. 
+The core of the system is efficient "dropless-MoE" and standard MoE layers. 
+Megablocks is integrated with `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`_, 
+where data and pipeline parallel training of MoEs is supported.
+
+* ROCm support for Megablocks is hosted in the official `https://github.com/ROCm/megablocks <https://github.com/ROCm/megablocks>`_ repository. 
+* Due to independent compatibility considerations, this location differs from the `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`_ upstream repository. 
+* Use the prebuilt :ref:`Docker image <megablocks-docker-compat>` with ROCm, PyTorch, and Megablocks preinstalled. 
+* See the :doc:`ROCm Megablocks installation guide <rocm-install-on-linux:install/3rd-party/megablocks-install>` to install and get started.
+
+.. note::
+
+  Megablocks is supported on ROCm 6.3.0.
+
+Supported devices
+================================================================================
+
+- **Officially Supported**: AMD Instinct MI300X
+- **Partially Supported** (functionality or performance limitations): AMD Instinct MI250X, MI210X
+
+Supported models and features
+================================================================================
+
+This section summarizes the Megablocks features supported by ROCm.
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+* dropless-Mixture-of-Experts
+
+
+.. _megablocks-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The `ROCm Megablocks blog posts <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`_ 
+guide how to leverage the ROCm platform for pre-training using the Megablocks framework. 
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training
+
+
+.. _megablocks-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`_
+with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest Megatron-LM version from the official Docker Hub.
+The Docker images have been validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Megablocks
+      - PyTorch
+      - Ubuntu
+      - Python
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+
+

docs/compatibility/ml-compatibility/pytorch-compatibility.rst

@@ -95,7 +95,7 @@ Docker image compatibility
 
 AMD validates and publishes `PyTorch images <https://hub.docker.com/r/rocm/pytorch>`__
 with ROCm backends on Docker Hub. The following Docker image tags and associated
-inventories were tested on `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__.
+inventories were tested on `ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__.
 Click |docker-icon| to view the image on Docker Hub.
 
 .. list-table:: PyTorch Docker image components
@@ -112,127 +112,118 @@ Click |docker-icon| to view the image on Docker Hub.
       - MAGMA
       - UCX
       - OMPI
-      - OFED
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-c76af9bfb1c25b0f40d4c29e8652105c57250bf018d23ff595b06bd79666fdd7"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-6a287591500b4048a9556c1ecc92bc411fd3d552f6c8233bc399f18eb803e8d6"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`__
       - 24.04
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`__
       - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0 <https://github.com/openucx/ucx/tree/v1.16.0>`__
+      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-f9d226135d51831c810dcb1251636ec61f85c65fcdda03e188c053a5d4f6585b"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-06b967629ba6657709f04169832cd769a11e6b491e8b1394c361d42d7a0c8b43"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`__
       - 22.04
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
       - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`__
       - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
       - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-3490e74d4f43dcdb3351dd334108d1ccd47e5a687c0523a2424ac1bcdd3dd6dd"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-62022414217ef6de33ac5b1341e57db8a48e8573fa2ace12d48aa5edd4b99ef0"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
       - 24.04
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
       - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.10.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-26c5dfffb4a54625884abca83166940f17dd27bc75f1b24f6e80fbcb7d4e9afb"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.11_pytorch_release_2.5.1/images/sha256-469a7f74fc149aff31797e011ee41978f6a190adc69fa423b3c6a718a77bd985"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
       - 22.04
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `3.11 <https://www.python.org/downloads/release/python-31113/>`__
       - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
       - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
       - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-f378a24561fa6efc178b6dc93fc7d82e5b93653ecd59c89d4476674d29e1284d"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-37f41a1cd94019688669a1b20d33ea74156e0c129ef6b8270076ef214a6a1a2c"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
+      - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
+      - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `master <https://bitbucket.org/icl/magma/src/master/>`__
+      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
+      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-60824ba83dc1b9d94164925af1f81c0235c105dd555091ec04c57e05177ead1b"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
       - 24.04
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`__
       - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-2308dbd0e650b7bf8d548575cbb6e2bdc021f9386384ce570da16d58ee684d22"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-fe944fe083312f901be6891ab4d3ffebf2eaf2cf4f5f0f435ef0b76ec714fabd"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
       - 22.04
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
       - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`__
       - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
       - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-eefd2ab019728f91f94c5e6a9463cb0ea900b3011458d18fe5d88e50c0b57d86"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-1d59251c47170c5b8960d1172a4dbe52f5793d8966edd778f168eaf32d56661a"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`__
       - 24.04
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`__
       - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`__
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-473643226ab0e93a04720b256ed772619878abf9c42b9f84828cefed522696fd"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`__
-      - 22.04
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
-      - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`__
-      - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
-      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
 Key ROCm libraries for PyTorch
 ================================================================================

docs/compatibility/ml-compatibility/tensorflow-compatibility.rst

@@ -56,7 +56,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `TensorFlow images
 <https://hub.docker.com/r/rocm/tensorflow>`__ with ROCm backends on
 Docker Hub. The following Docker image tags and associated inventories are
-validated for `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__. Click
+validated for `ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__. Click
 the |docker-icon| icon to view the image on Docker Hub.
 
 .. list-table:: TensorFlow Docker image components
@@ -65,128 +65,61 @@ the |docker-icon| icon to view the image on Docker Hub.
     * - Docker image
       - TensorFlow
       - Ubuntu
-      - Dev
       - Python
       - TensorBoard
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.18-dev/images/sha256-fa9cf5fa6c6079a7118727531ccd0056c6e3224a42c3d6e78a49e7781daafff4"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.18-dev/images/sha256-96754ce2d30f729e19b497279915b5212ba33d5e408e7e5dd3f2304d87e3441e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
       - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.18-runtime/images/sha256-d14d8c4989e7c9a60f4e72461b9e349de72347c6162dcd6897e6f4f80ffbb440"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.18-dev/images/sha256-fa741508d383858e86985a9efac85174529127408102558ae2e3a4ac894eea1e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - runtime
+      - 22.04
-      - 24.04
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.18-dev/images/sha256-081e5bd6615a5dc17247ebd2ccc26895c3feeff086720400fa39b477e60a77c0"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.17-dev/images/sha256-3a0aef09f2a8833c2b64b85874dd9449ffc2ad257351857338ff5b706c03a418"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
-      - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.18-runtime/images/sha256-bf369637378264f4af6ddad5ca8b8611d3e372ffbea9ab7a06f1e122f0a0867b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.17-dev/images/sha256-5a502008c50d0b6508e6027f911bdff070a7493700ae064bed74e1d22b91ed50"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
       - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.17-runtime/images/sha256-1ee5dfffceb71ac66617ada33de3a10de0cb74199cc4b82441192e5e92fa2ddf"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.17-dev/images/sha256-bc7341a41ebe7ab261aa100732874507c452421ef733e408ac4f05ed453b0bc5"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-3124/>`__
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-dev/images/sha256-109218ad92bfae83bbd2710475f7502166e1ed54ca0b9748a9cbc3f5a1d75af1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
       - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-runtime/images/sha256-5d78bd5918d394f92263daa2990e88d695d27200dd90ed83ec64d20c7661c9c1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.16-dev/images/sha256-4841a8df7c340dab79bf9362dad687797649a00d594e0832eb83ea6880a40d3b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.16-dev/images/sha256-b09b1ad921c09c687b7c916141051e9fcf15539a5686e5aa67c689195a522719"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
       - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.16-runtime/images/sha256-20dbd824e85558abfe33fc9283cc547d88cde3c623fe95322743a5082f883a64"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.16-dev/images/sha256-883fa95aba960c58a3e46fceaa18f03ede2c7df89b8e9fd603ab2d47e0852897"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.16.2-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377>`__
-      - dev
       - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-runtime/images/sha256-a94150ffb81365234ebfa34e764db5474bc6ab7d141b56495eac349778dafcf3"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
       - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
 
 

docs/compatibility/ml-compatibility/verl-compatibility.rst

@@ -16,56 +16,25 @@ verl offers a scalable, open-source fine-tuning solution optimized for AMD Insti
 * See the `verl documentation <https://verl.readthedocs.io/en/latest/>`_ for more information about verl. 
 * The official verl GitHub repository is `https://github.com/volcengine/verl <https://github.com/volcengine/verl>`_.
 * Use the AMD-validated :ref:`Docker images <verl-docker-compat>` with ROCm and verl preinstalled. 
-* See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>` to get started.
+* See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>` to install and get started.
 
 .. note::
 
 	verl is supported on ROCm 6.2.0.
 
-
 .. _verl-recommendations:
 
 Use cases and recommendations
 ================================================================================
 
-The benefits of verl in large-scale reinforcement leaning from human feedback (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`_ blog.
+The benefits of verl in large-scale reinforcement learning from human feedback (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`_ blog.
-
-.. _verl-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `ROCm verl Docker images <https://hub.docker.com/r/rocm/verl>`_
-with ROCm backends on Docker Hub. The following Docker image tags and associated inventories represent the latest verl version from the official Docker Hub. The Docker images have been validated for `ROCm 6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`_. 
-
-.. list-table:: 
-    :header-rows: 1
-
-    *   - Docker image
-        - verl
-        - Linux
-        - Pytorch
-        - Python
-        - vllm
-
-    *   - .. raw:: html
-
-            <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
-        - `0.3.0post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`_
-        - Ubuntu 20.04
-        - `2.5.0 <https://download.pytorch.org/whl/cu118/torch-2.5.0%2Bcu118-cp39-cp39-linux_x86_64.whl#sha256=1ee24b267418c37b297529ede875b961e382c1c365482f4142af2398b92ed127>`_
-        - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`_
-        - `0.6.4 <https://github.com/vllm-project/vllm/releases/tag/v0.6.4>`_
 
+.. _verl-supported_features:
 
 Supported features
 ===============================================================================
 
-The following table shows verl and ROCm support for GPU-accelerated modules.
+The following table shows verl on ROCm support for GPU-accelerated modules.
 
 .. list-table::
     :header-rows: 1
@@ -77,9 +46,41 @@ The following table shows verl and ROCm support for GPU-accelerated modules.
     * - ``FSDP``
       - Training engine
       - 0.3.0.post0
-      - 6.2
+      - 6.2.0
     * - ``vllm``
       - Inference engine
       - 0.3.0.post0
-      - 6.2
+      - 6.2.0
-  
+
+.. _verl-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes ready-made `ROCm verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
+with ROCm backends on Docker Hub. The following Docker image tags and associated inventories represent the available verl versions from the official Docker Hub. 
+
+.. list-table:: 
+    :header-rows: 1
+
+    *   - Docker image
+        - ROCm
+        - verl
+        - Ubuntu
+        - Pytorch
+        - Python
+        - vllm
+
+    *   - .. raw:: html
+
+            <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+        - `6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`_
+        - `0.3.0post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`_
+        - 20.04
+        - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`_
+        - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`_
+        - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`_

docs/conf.py

@@ -96,6 +96,10 @@ article_pages = [
     {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/jax-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/verl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/stanford-megatron-lm-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
     {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},

docs/data/how-to/rocm-for-ai/inference/pytorch-inference-benchmark-models.yaml

@@ -1,6 +1,6 @@
 pytorch_inference_benchmark:
   unified_docker:
-    latest: &rocm-pytorch-docker-latest
+    latest:
       pull_tag: rocm/pytorch:latest
       docker_hub_url:
       rocm_version:
@@ -39,3 +39,11 @@ pytorch_inference_benchmark:
         model_repo: Wan-AI/Wan2.1-T2V-14B
         url: https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
         precision: bfloat16
+    - group: Janus-Pro
+      tag: janus-pro
+      models:
+      - model: Janus Pro 7B
+        mad_tag: pyt_janus_pro_inference
+        model_repo: deepseek-ai/Janus-Pro-7B
+        url: https://huggingface.co/deepseek-ai/Janus-Pro-7B
+        precision: bfloat16

docs/data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml

@@ -0,0 +1,17 @@
+sglang_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: lmsysorg/sglang:v0.4.5-rocm630
+      docker_hub_url: https://hub.docker.com/layers/lmsysorg/sglang/v0.4.5-rocm630/images/sha256-63d2cb760a237125daf6612464cfe2f395c0784e21e8b0ea37d551cd10d3c951
+      rocm_version: 6.3.0
+      sglang_version: 0.4.5 (0.4.5-rocm)
+      pytorch_version: 2.6.0a0+git8d4926e
+  model_groups:
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek-R1-Distill-Qwen-32B
+        mad_tag: pyt_sglang_deepseek-r1-distill-qwen-32b
+        model_repo: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+        precision: bfloat16

docs/how-to/deep-learning-rocm.rst

@@ -20,6 +20,7 @@ features for these ROCm-enabled deep learning frameworks.
 * :doc:`verl compatibility <../compatibility/ml-compatibility/verl-compatibility>`
 * :doc:`Stanford Megatron-LM compatibility <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
 * :doc:`DGL compatibility <../compatibility/ml-compatibility/dgl-compatibility>`
+* :doc:`Megablocks compatibility <../compatibility/ml-compatibility/megablocks-compatibility>`
 
 This chart steps through typical installation workflows for installing deep learning frameworks for ROCm.
 
@@ -35,6 +36,7 @@ See the installation instructions to get started.
 * :doc:`verl for ROCm <rocm-install-on-linux:install/3rd-party/verl-install>`
 * :doc:`Stanford Megatron-LM for ROCm <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
 * :doc:`DGL for ROCm <rocm-install-on-linux:install/3rd-party/dgl-install>`
+* :doc:`Megablocks for ROCm <rocm-install-on-linux:install/3rd-party/megablocks-install>`
 
 .. note::
 

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/sglang-history.rst

@@ -0,0 +1,25 @@
+:orphan:
+
+****************************************************
+SGLang inference performance testing version history
+****************************************************
+
+This table lists previous versions of the ROCm SGLang inference performance
+testing environment. For detailed information about available models for
+benchmarking, see the version-specific documentation.
+
+.. list-table::
+   :header-rows: 1
+
+   * - Docker image tag
+     - Components
+     - Resources
+
+   * - ``lmsysorg/sglang:v0.4.5-rocm630``
+     - 
+       * ROCm 6.3.0
+       * SGLang 0.4.5
+       * PyTorch 2.6.0
+     - 
+       * :doc:`Documentation <../sglang>`
+       * `Docker Hub <https://hub.docker.com/layers/lmsysorg/sglang/v0.4.5-rocm630/images/sha256-63d2cb760a237125daf6612464cfe2f395c0784e21e8b0ea37d551cd10d3c951>`__

docs/how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst

@@ -103,7 +103,7 @@ PyTorch inference performance testing
 
          The Chai-1 benchmark uses a specifically selected Docker image using ROCm 6.2.3 and PyTorch 2.3.0 to address an accuracy issue.
 
-   .. container:: model-doc pyt_clip_inference pyt_mochi_video_inference pyt_wan2.1_inference
+   .. container:: model-doc pyt_clip_inference pyt_mochi_video_inference pyt_wan2.1_inference pyt_janus_pro_inference
 
       Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/latest/images/sha256-05b55983e5154f46e7441897d0908d79877370adca4d1fff4899d9539d6c4969>`__ from Docker Hub.
 
@@ -140,22 +140,27 @@ PyTorch inference performance testing
       .. code-block:: shell
 
          export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-         python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+         madengine run \
+             --tags {{model.mad_tag}} \
+             --keep-model-dir \
+             --live-output \
+             --timeout 28800
 
       MAD launches a Docker container with the name
       ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
-      model are collected in ``perf.csv``.
+      model are collected in ``perf_{{model.mad_tag}}.csv``.
 
+      {% if model.mad_tag != "pyt_janus_pro_inference" %}
       .. note::
 
          For improved performance, consider enabling TunableOp. By default,
          ``{{model.mad_tag}}`` runs with TunableOp disabled (see
          `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To enable
-         it, edit the default run behavior in the ``tools/run_models.py``-- update the model's
+         it, include the ``--tunableop on`` argument in your run.
-         run ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
 
          Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
          Although this might increase the initial training time, it can result in a performance gain.
+      {% endif %}
 
       {% endfor %}
    {% endfor %}
@@ -163,8 +168,10 @@ PyTorch inference performance testing
 Further reading
 ===============
 
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
 - To learn more about system settings and management practices to configure your system for
-  MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`../../inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang.rst

@@ -0,0 +1,280 @@
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and SGLang
+   :keywords: model, MAD, automation, dashboarding, validate
+
+************************************
+SGLang inference performance testing
+************************************
+
+.. _sglang-benchmark-unified-docker:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml
+
+   {% set unified_docker = data.sglang_benchmark.unified_docker.latest %}
+
+   `SGLang <https://docs.sglang.ai>`__ is a high-performance inference and
+   serving engine for large language models (LLMs) and vision models. The
+   ROCm-enabled `SGLang Docker image <{{ unified_docker.docker_hub_url }}>`__
+   bundles SGLang with PyTorch, optimized for AMD Instinct MI300X series
+   accelerators. It includes the following software components:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      * - `ROCm <https://github.com/ROCm/ROCm>`__
+        - {{ unified_docker.rocm_version }}
+
+      * - `SGLang <https://docs.sglang.ai/index.html>`__
+        - {{ unified_docker.sglang_version }} 
+
+      * - `PyTorch <https://github.com/pytorch/pytorch>`__
+        - {{ unified_docker.pytorch_version }} 
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml
+
+   {% set unified_docker = data.sglang_benchmark.unified_docker.latest %}
+   {% set model_groups = data.sglang_benchmark.model_groups %}
+
+   Pull the Docker image
+   =====================
+
+   Download the `SGLang Docker image <{{ unified_docker.docker_hub_url }}>`__.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose one of the following methods to benchmark inference performance with
+   `DeepSeek-R1-Distill-Qwen-32B <https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B>`__.
+
+   .. _sglang-benchmark-mad:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+               using one GPU with the ``{{model.precision}}`` data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/perf_DeepSeek-R1-Distill-Qwen-32B.csv``.
+
+            Although the DeepSeek-R1-Distill-Qwen-32B is preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
+
+         .. tab-item:: Standalone benchmarking
+
+            .. rubric:: Download the Docker image and required scripts
+
+            1. Run the SGLang benchmark script independently by starting the
+               `Docker container <{{ unified_docker.docker_hub_url }}>`__
+               as shown in the following snippet.
+
+               .. code-block:: shell
+
+                  docker pull {{ unified_docker.pull_tag }}
+                  docker run -it \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --shm-size 16G \
+                      --security-opt seccomp=unconfined \
+                      --security-opt apparmor=unconfined \
+                      --cap-add=SYS_PTRACE \
+                      -v $(pwd):/workspace \
+                      --env HUGGINGFACE_HUB_CACHE=/workspace \
+                      --name test \
+                      {{ unified_docker.pull_tag }}
+
+            2. In the Docker container, clone the ROCm MAD repository and navigate to the
+               benchmark scripts directory at ``~/MAD/scripts/sglang``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/sglang
+
+            3. To start the benchmark, use the following command with the appropriate options.
+
+               .. dropdown:: Benchmark options
+                  :open:
+
+                  .. list-table::
+                     :header-rows: 1
+                     :align: center
+
+                     * - Name
+                       - Options
+                       - Description
+
+                     * - ``$test_option``
+                       - latency
+                       - Measure decoding token latency
+
+                     * -
+                       - throughput
+                       - Measure token generation throughput
+
+                     * -
+                       - all
+                       - Measure both throughput and latency
+
+                     * - ``$num_gpu``
+                       - 8
+                       - Number of GPUs
+
+                     * - ``$datatype``
+                       - ``bfloat16``
+                       - Data type
+
+                     * - ``$dataset``
+                       - random
+                       - Dataset
+
+                  The input sequence length, output sequence length, and tensor parallel (TP) are
+                  already configured. You don't need to specify them with this script.
+
+               Command:
+
+               .. code-block:: shell
+
+                  ./sglang_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d $datatype [-a $dataset]
+
+            .. note::
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block:: shell-session
+
+                  OSError: You are trying to access a gated repo.
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            .. rubric:: Benchmarking examples
+
+            Here are some examples of running the benchmark with various options:
+
+            * Latency benchmark
+
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./sglang_benchmark_report.sh \
+                     -s latency \
+                     -m {{model.model_repo}} \
+                     -g 8 \
+                     -d {{model.precision}}
+
+              Find the latency report at ``./reports_{{model.precision}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+
+            * Throughput benchmark
+
+              Use this command to benchmark the throughput of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./sglang_benchmark_report.sh \
+                     -s throughput \
+                     -m {{model.model_repo}} \
+                     -g 8 \
+                     -d {{model.precision}} \
+                     -a random
+
+              Find the throughput report at ``./reports_{{model.precision}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/sgl-project/sglang/tree/main/benchmark/blog_v0_2>`__.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- To learn how to run community models from Hugging Face on AMD GPUs, see
+  :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.
+
+- To learn how to fine-tune LLMs and optimize inference, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference>`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`previous-versions/sglang-history` to find documentation for previous releases
+of SGLang inference performance testing.

docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst

@@ -202,7 +202,7 @@ system's configuration.
                .. code-block:: shell
 
                   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-                  python3 tools/run_models.py \
+                  madengine run \
                       --tags {{model.mad_tag}} \
                       --keep-model-dir \
                       --live-output \
@@ -226,12 +226,12 @@ system's configuration.
 
                By default, ``{{model.mad_tag}}`` runs with TunableOp disabled
                (see
-               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__).
-               enable it, edit the default run behavior in the ``models.json``
+               To enable it, include the ``--tunableop on`` argument in your
-               configuration before running inference -- update the model's run
+               run.
-               ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
 
-               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed
+               by the performance-collection run.
 
             {% endif %}
 
@@ -419,8 +419,10 @@ Further reading
 - To learn more about the options for latency and throughput benchmark scripts,
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/index.rst

@@ -24,4 +24,6 @@ training, fine-tuning, and inference. It leverages popular machine learning fram
 
 - :doc:`PyTorch inference performance testing <benchmark-docker/pytorch-inference>`
 
+- :doc:`SGLang inference performance testing <benchmark-docker/sglang>`
+
 - :doc:`Deploying your model <deploy-your-model>`

docs/how-to/rocm-for-ai/install.rst

@@ -24,12 +24,13 @@ If you’re new to ROCm, refer to the :doc:`ROCm quick start install guide for L
 If you’re using a Radeon GPU for graphics-accelerated applications, refer to the
 `Radeon installation instructions <https://rocm.docs.amd.com/projects/radeon/en/docs-6.1.3/docs/install/native_linux/install-radeon.html>`_.
 
-ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install/install-overview>`:
+You can install ROCm on :doc:`compatible systems <rocm-install-on-linux:reference/system-requirements>` via your Linux
+distribution's package manager. See the following documentation resources to get started:
+
+* :doc:`ROCm installation overview <rocm-install-on-linux:install/install-overview>`
 
 * :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
 
-* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/install-methods/amdgpu-installer-index>`
-
 * :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`
 
 .. grid:: 1
@@ -59,6 +60,12 @@ images with the framework pre-installed.
 
 * :doc:`JAX for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
 
+* :doc:`verl for ROCm <rocm-install-on-linux:install/3rd-party/verl-install>`
+
+* :doc:`Stanford Megatron-LM for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
+
+* :doc:`DGL for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
+
 Next steps
 ==========
 

docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst

@@ -73,7 +73,11 @@ document are not validated.
 
       .. code-block:: shell
 
-         python3 tools/run_models.py --tags pyt_mpt30b_training --keep-model-dir --live-output --clean-docker-cache
+         madengine run \
+             --tags pyt_mpt30b_training \
+             --keep-model-dir \
+             --live-output \
+             --clean-docker-cache
 
       .. tip::
 
@@ -90,7 +94,7 @@ document are not validated.
 
          For improved performance (training throughput), consider enabling TunableOp.
          By default, ``pyt_mpt30b_training`` runs with TunableOp disabled. To enable it,
-         run ``tools/run_models.py`` with the ``--tunableop on`` argument or edit the
+         run ``madengine run`` with the ``--tunableop on`` argument or edit the
          ``models.json`` configuration before running training.
 
          Although this might increase the initial training time, it can result in a performance gain.
@@ -172,4 +176,13 @@ Key performance metrics include:
 
     Overall training loss. A decreasing trend indicates the model is learning effectively.
 
+Further reading
+===============
 
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst

@@ -142,7 +142,11 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
             .. code-block:: shell
 
                export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-               python3 tools/run_models.py --tags {{ model.mad_tag }} --keep-model-dir --live-output --timeout 28800
+               madengine run \
+                   --tags {{ model.mad_tag }} \
+                   --keep-model-dir \
+                   --live-output \
+                   --timeout 28800
 
             MAD launches a Docker container with the name
             ``container_ci-{{ model.mad_tag }}``, for example. The latency and throughput reports of the
@@ -427,6 +431,17 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
 
                For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
 
+Further reading
+===============
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
 Previous versions
 =================
 

docs/reference/gpu-arch-specs.rst

@@ -285,7 +285,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - Radeon AI PRO R9700
           - RDNA4
           - gfx1201
-          - 16
+          - 32
           - 64
           - 32 or 64
           - 128

docs/reference/graph-safe-support.rst

@@ -93,7 +93,7 @@ The following table shows whether a ROCm library is graph-safe.
       - ⚠️ (experimental)
     * 
       - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - ❌ (see :doc:`details <rocthrust:hipgraph-support>`)
+      - ❌ (see :doc:`details <rocthrust:reference/rocThrust-hipgraph-support>`)
     * 
       - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
       - ❌

docs/sphinx/_toc.yml.in

@@ -19,9 +19,9 @@ subtrees:
 
 - caption: Install
   entries:
-  - url: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/
+  - url: https://rocm.docs.amd.com/projects/install-on-linux/en/${branch}/
     title: ROCm on Linux
-  - url: https://rocm.docs.amd.com/projects/install-on-windows/en/${branch}/
+  - url: https://rocm.docs.amd.com/projects/install-on-windows/en/latest/
     title: HIP SDK on Windows
   - url: https://rocm.docs.amd.com/projects/radeon/en/latest/index.html
     title: ROCm on Radeon GPUs
@@ -82,6 +82,8 @@ subtrees:
             title: vLLM inference performance testing
           - file: how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst
             title: PyTorch inference performance testing
+          - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang.rst
+            title: SGLang inference performance testing
           - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
             title: Deploy your model
 

docs/sphinx/requirements.in

@@ -1,4 +1,4 @@
-rocm-docs-core==1.20.1
+rocm-docs-core==1.26.0
 sphinx-reredirects
 sphinx-sitemap
 sphinxcontrib.datatemplates==0.11.0

docs/sphinx/requirements.txt

@@ -10,7 +10,7 @@ alabaster==1.0.0
     # via sphinx
 asttokens==3.0.0
     # via stack-data
-attrs==25.3.0
+attrs==25.4.0
     # via
     #   jsonschema
     #   jupyter-cache
@@ -19,34 +19,32 @@ babel==2.17.0
     # via
     #   pydata-sphinx-theme
     #   sphinx
-beautifulsoup4==4.13.4
+beautifulsoup4==4.14.2
     # via pydata-sphinx-theme
 breathe==4.36.0
     # via rocm-docs-core
-certifi==2025.4.26
+certifi==2025.10.5
     # via requests
-cffi==1.17.1
+cffi==2.0.0
     # via
     #   cryptography
     #   pynacl
-charset-normalizer==3.4.2
+charset-normalizer==3.4.4
     # via requests
-click==8.2.1
+click==8.3.0
     # via
     #   jupyter-cache
     #   sphinx-external-toc
-comm==0.2.2
+comm==0.2.3
     # via ipykernel
-cryptography==45.0.3
+cryptography==46.0.2
     # via pyjwt
-debugpy==1.8.14
+debugpy==1.8.17
     # via ipykernel
 decorator==5.2.1
     # via ipython
 defusedxml==0.7.1
     # via sphinxcontrib-datatemplates
-deprecated==1.2.18
-    # via pygithub
 docutils==0.21.2
     # via
     #   myst-parser
@@ -54,19 +52,19 @@ docutils==0.21.2
     #   sphinx
 exceptiongroup==1.3.0
     # via ipython
-executing==2.2.0
+executing==2.2.1
     # via stack-data
-fastjsonschema==2.21.1
+fastjsonschema==2.21.2
     # via
     #   nbformat
     #   rocm-docs-core
 gitdb==4.0.12
     # via gitpython
-gitpython==3.1.44
+gitpython==3.1.45
     # via rocm-docs-core
-greenlet==3.2.3
+greenlet==3.2.4
     # via sqlalchemy
-idna==3.10
+idna==3.11
     # via requests
 imagesize==1.4.1
     # via sphinx
@@ -74,7 +72,7 @@ importlib-metadata==8.7.0
     # via
     #   jupyter-cache
     #   myst-nb
-ipykernel==6.29.5
+ipykernel==7.0.0
     # via myst-nb
 ipython==8.37.0
     # via
@@ -86,9 +84,9 @@ jinja2==3.1.6
     # via
     #   myst-parser
     #   sphinx
-jsonschema==4.24.0
+jsonschema==4.25.1
     # via nbformat
-jsonschema-specifications==2025.4.1
+jsonschema-specifications==2025.9.1
     # via jsonschema
 jupyter-cache==1.0.1
     # via myst-nb
@@ -106,17 +104,17 @@ markdown-it-py==3.0.0
     # via
     #   mdit-py-plugins
     #   myst-parser
-markupsafe==3.0.2
+markupsafe==3.0.3
     # via jinja2
 matplotlib-inline==0.1.7
     # via
     #   ipykernel
     #   ipython
-mdit-py-plugins==0.4.2
+mdit-py-plugins==0.5.0
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-nb==1.2.0
+myst-nb==1.3.0
     # via rocm-docs-core
 myst-parser==4.0.1
     # via myst-nb
@@ -134,31 +132,30 @@ nest-asyncio==1.6.0
 packaging==25.0
     # via
     #   ipykernel
-    #   pydata-sphinx-theme
     #   sphinx
-parso==0.8.4
+parso==0.8.5
     # via jedi
 pexpect==4.9.0
     # via ipython
-platformdirs==4.3.8
+platformdirs==4.5.0
     # via jupyter-core
-prompt-toolkit==3.0.51
+prompt-toolkit==3.0.52
     # via ipython
-psutil==7.0.0
+psutil==7.1.0
     # via ipykernel
 ptyprocess==0.7.0
     # via pexpect
 pure-eval==0.2.3
     # via stack-data
-pycparser==2.22
+pycparser==2.23
     # via cffi
-pydata-sphinx-theme==0.15.4
+pydata-sphinx-theme==0.16.1
     # via
     #   rocm-docs-core
     #   sphinx-book-theme
-pygithub==2.6.1
+pygithub==2.8.1
     # via rocm-docs-core
-pygments==2.19.1
+pygments==2.19.2
     # via
     #   accessible-pygments
     #   ipython
@@ -166,11 +163,11 @@ pygments==2.19.1
     #   sphinx
 pyjwt[crypto]==2.10.1
     # via pygithub
-pynacl==1.5.0
+pynacl==1.6.0
     # via pygithub
 python-dateutil==2.9.0.post0
     # via jupyter-client
-pyyaml==6.0.2
+pyyaml==6.0.3
     # via
     #   jupyter-cache
     #   myst-nb
@@ -178,21 +175,21 @@ pyyaml==6.0.2
     #   rocm-docs-core
     #   sphinx-external-toc
     #   sphinxcontrib-datatemplates
-pyzmq==26.4.0
+pyzmq==27.1.0
     # via
     #   ipykernel
     #   jupyter-client
-referencing==0.36.2
+referencing==0.37.0
     # via
     #   jsonschema
     #   jsonschema-specifications
-requests==2.32.4
+requests==2.32.5
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.20.1
+rocm-docs-core==1.26.0
     # via -r requirements.in
-rpds-py==0.25.1
+rpds-py==0.27.1
     # via
     #   jsonschema
     #   referencing
@@ -202,7 +199,7 @@ smmap==5.0.2
     # via gitdb
 snowballstemmer==3.0.1
     # via sphinx
-soupsieve==2.7
+soupsieve==2.8
     # via beautifulsoup4
 sphinx==8.1.3
     # via
@@ -220,7 +217,7 @@ sphinx==8.1.3
     #   sphinx-reredirects
     #   sphinxcontrib-datatemplates
     #   sphinxcontrib-runcmd
-sphinx-book-theme==1.1.4
+sphinx-book-theme==1.1.3
     # via rocm-docs-core
 sphinx-copybutton==0.5.2
     # via rocm-docs-core
@@ -234,7 +231,7 @@ sphinx-notfound-page==1.1.0
     # via rocm-docs-core
 sphinx-reredirects==0.1.6
     # via -r requirements.in
-sphinx-sitemap==2.7.2
+sphinx-sitemap==2.9.0
     # via -r requirements.in
 sphinxcontrib-applehelp==2.0.0
     # via sphinx
@@ -252,21 +249,20 @@ sphinxcontrib-runcmd==0.2.0
     # via sphinxcontrib-datatemplates
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-sqlalchemy==2.0.41
+sqlalchemy==2.0.44
     # via jupyter-cache
 stack-data==0.6.3
     # via ipython
 tabulate==0.9.0
     # via jupyter-cache
-tomli==2.2.1
+tomli==2.3.0
     # via sphinx
-tornado==6.5.1
+tornado==6.5.2
     # via
     #   ipykernel
     #   jupyter-client
 traitlets==5.14.3
     # via
-    #   comm
     #   ipykernel
     #   ipython
     #   jupyter-client
@@ -274,9 +270,10 @@ traitlets==5.14.3
     #   matplotlib-inline
     #   nbclient
     #   nbformat
-typing-extensions==4.14.0
+typing-extensions==4.15.0
     # via
     #   beautifulsoup4
+    #   cryptography
     #   exceptiongroup
     #   ipython
     #   myst-nb
@@ -288,9 +285,7 @@ urllib3==2.5.0
     # via
     #   pygithub
     #   requests
-wcwidth==0.2.13
+wcwidth==0.2.14
     # via prompt-toolkit
-wrapt==1.17.2
-    # via deprecated
 zipp==3.23.0
     # via importlib-metadata