Revert "wavesize Release Note update (#4372)"

This reverts commit 1ad5a42302.

.azuredevops/tag-builds/TransferBench.yml

@@ -1,29 +0,0 @@
-variables:
-- group: common
-- template: /.azuredevops/variables-global.yml
-
-parameters:
-- name: checkoutRef
-  type: string
-  default: refs/tags/$(LATEST_RELEASE_TAG)
-
-resources:
-  repositories:
-  - repository: pipelines_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/ROCm
-  - repository: release_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/TransferBench
-    ref: ${{ parameters.checkoutRef }}
-
-trigger: none
-pr: none
-
-jobs:
-  - template: ${{ variables.CI_COMPONENT_PATH }}/TransferBench.yml
-    parameters:
-      checkoutRepo: release_repo
-      checkoutRef: ${{ parameters.checkoutRef }}

.wordlist.txt

@@ -74,6 +74,7 @@ Conda
 ConnectX
 CuPy
 Dashboarding
+DBRX
 DDR
 DF
 DGEMM
@@ -92,6 +93,7 @@ DataFrame
 DataLoader
 DataParallel
 Debian
+DeepSeek
 DeepSpeed
 Dependabot
 Deprecations
@@ -129,6 +131,7 @@ GDS
 GEMM
 GEMMs
 GFortran
+Gemma
 GiB
 GIM
 GL
@@ -151,6 +154,7 @@ HCA
 HGX
 HIPCC
 HIPExtension
+HIPification
 HIPIFY
 HIPification
 HIPify

RELEASE.md

@@ -29,8 +29,7 @@ The release notes provide a summary of notable changes since the previous ROCm r
 - [ROCm upcoming changes](#rocm-upcoming-changes)
 
 ```{note}
-If you’re using Radeon™ PRO or Radeon GPUs in a workstation setting with a
-display connected, continue to use ROCm 6.2.3. See the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/index.html)
+If you’re using Radeon™ PRO or Radeon GPUs in a workstation setting with a display connected, see the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility/native_linux/native_linux_compatibility.html)
 documentation to verify compatibility and system requirements.
 ```
 ## Release highlights

docs/about/license.md

@@ -62,7 +62,7 @@ additional licenses. Please review individual repositories for more information.
 | [rocJPEG](https://github.com/ROCm/rocJPEG/) | [MIT](https://github.com/ROCm/rocJPEG/blob/develop/LICENSE) |
 | [ROCK-Kernel-Driver](https://github.com/ROCm/ROCK-Kernel-Driver/) | [GPL 2.0 WITH Linux-syscall-note](https://github.com/ROCm/ROCK-Kernel-Driver/blob/master/COPYING) |
 | [rocminfo](https://github.com/ROCm/rocminfo/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocminfo/blob/amd-staging/License.txt) |
-| [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |
+| [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [MIT](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |
 | [ROCm CMake](https://github.com/ROCm/rocm-cmake/) | [MIT](https://github.com/ROCm/rocm-cmake/blob/develop/LICENSE) |
 | [ROCm Communication Collectives Library (RCCL)](https://github.com/ROCm/rccl/) | [Custom](https://github.com/ROCm/rccl/blob/develop/LICENSE.txt) |
 | [ROCm-Core](https://github.com/ROCm/rocm-core) | [MIT](https://github.com/ROCm/rocm-core/blob/master/copyright) |

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

@@ -7,7 +7,7 @@ ROCm Version,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.2, 6.1.1, 6.1.0, 6.0
       ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
       ,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
       ,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,,,
-,Debian 12 [#mi300x-past-60]_,Debian 12 [#mi300x-past-60]_,,,,,,,,,,
+,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,
 ,Azure Linux 3.0 [#mi300x-past-60]_,,,,,,,,,,,
       ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,
       :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3

docs/compatibility/compatibility-matrix.rst

@@ -32,7 +32,7 @@ compatibility and system requirements.
       ,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9"
       ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5"
       ,Oracle Linux 8.10 [#mi300x]_,Oracle Linux 8.10 [#mi300x]_,Oracle Linux 8.9 [#mi300x]_
-      ,Debian 12 [#mi300x]_,Debian 12 [#mi300x]_,
+      ,Debian 12 [#single-node]_,Debian 12 [#single-node]_,
       ,Azure Linux 3.0 [#mi300x]_,,
       ,.. _architecture-support-compatibility-matrix:,,
       :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3
@@ -148,7 +148,8 @@ compatibility and system requirements.
 
 .. rubric:: Footnotes
 
-.. [#mi300x] Oracle Linux, Debian, and Azure Linux are supported only on AMD Instinct MI300X.
+.. [#mi300x] Oracle Linux and Azure Linux are supported only on AMD Instinct MI300X.
+.. [#single-node] Debian 12 is supported only on AMD Instinct MI300X for single-node functionality. 
 .. [#mi300_620] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
 .. [#kfd_support] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
 .. [#ROCT-rocr] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
@@ -215,7 +216,8 @@ Expand for full historical view of:
 
    .. rubric:: Footnotes
 
-   .. [#mi300x-past-60] Oracle Linux, Debian, and Azure Linux are supported only on AMD Instinct MI300X.
+   .. [#mi300x-past-60] Oracle Linux and Azure Linux are supported only on AMD Instinct MI300X.
+   .. [#single-node-past-60] Debian 12 is supported only on AMD Instinct MI300X for single-node functionality. 
    .. [#mi300_624-past-60] **For ROCm 6.2.4** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
    .. [#mi300_622-past-60] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
    .. [#mi300_621-past-60] **For ROCm 6.2.1** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].

docs/compatibility/pytorch-compatibility.rst

@@ -0,0 +1,916 @@
+.. meta::
+    :description: PyTorch compatibility
+    :keywords: GPU, PyTorch compatibility
+
+********************************************************************************
+PyTorch compatibility
+********************************************************************************
+
+`PyTorch <https://pytorch.org/>`_ is an open-source tensor library designed for
+deep learning. PyTorch on ROCm provides mixed-precision and large-scale training
+using `MIOpen <https://github.com/ROCm/MIOpen>`_ and
+`RCCL <https://github.com/ROCm/rccl>`_ libraries.
+
+ROCm support for PyTorch is upstreamed into the official PyTorch repository. Due to independent
+compatibility considerations, this results in two distinct release cycles for PyTorch on ROCm:
+
+- ROCm PyTorch release:
+
+  - Provides the latest version of ROCm but doesn't immediately support the latest stable PyTorch
+    version.
+
+  - Offers :ref:`Docker images <pytorch-docker-compat>` with ROCm and PyTorch
+    pre-installed.
+
+  - ROCm PyTorch repository: `<https://github.com/rocm/pytorch>`__
+
+  - See the :doc:`ROCm PyTorch installation guide <rocm-install-on-linux:install/3rd-party/pytorch-install>` to get started.
+
+- Official PyTorch release:
+
+  - Provides the latest stable version of PyTorch but doesn't immediately support the latest ROCm version.
+
+  - Official PyTorch repository: `<https://github.com/pytorch/pytorch>`__
+
+  - See the `Nightly and latest stable version installation guide <https://pytorch.org/get-started/locally/>`_
+    or `Previous versions <https://pytorch.org/get-started/previous-versions/>`_ to get started.
+
+The upstream PyTorch includes an automatic HIPification solution that automatically generates HIP
+source code from the CUDA backend. This approach allows PyTorch to support ROCm without requiring
+manual code modifications.
+
+ROCm's development is aligned with the stable release of PyTorch while upstream PyTorch testing uses
+the stable release of ROCm to maintain consistency.
+
+.. _pytorch-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+AMD validates and publishes ready-made `PyTorch <https://hub.docker.com/r/rocm/pytorch>`_
+images with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories are validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
+
+.. list-table:: PyTorch Docker image components
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker
+      - PyTorch
+      - Ubuntu
+      - Python
+      - Apex
+      - torchvision
+      - TensorBoard
+      - MAGMA
+      - UCX
+      - OMPI
+      - OFED
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu24.04_py3.12_pytorch_release_2.4.0/images/sha256-98ddf20333bd01ff749b8092b1190ee369a75d3b8c71c2fac80ffdcb1a98d529?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3128/>`_
+      - `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>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.4.0/images/sha256-402c9b4f1a6b5a81c634a1932b56cbe01abb699cfcc7463d226276997c6cf8ea?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `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>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.9_pytorch_release_2.4.0/images/sha256-e0608b55d408c3bfe5c19fdd57a4ced3e0eb3a495b74c309980b60b156c526dd?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.9 <https://www.python.org/downloads/release/python-3918/>`_
+      - `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>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-652cf25263d05b1de548222970aeb76e60b12de101de66751264709c0d0ff9d8?context=explore"><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 <https://www.python.org/downloads/release/python-31016/>`_
+      - `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/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.2.1/images/sha256-051976f26beab8f9aa65d999e3ad546c027b39240a0cc3ee81b114a9024f2912?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `1.2.0 <https://github.com/ROCm/apex/tree/release/1.2.0>`_
+      - `0.17.1 <https://github.com/pytorch/vision/tree/v0.17.1>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `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/rocm6.3_ubuntu20.04_py3.9_pytorch_release_2.2.1/images/sha256-88c839a364d109d3748c100385bfa100d28090d25118cc723fd0406390ab2f7e?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
+      - 20.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.2.0 <https://github.com/ROCm/apex/tree/release/1.2.0>`_
+      - `0.17.1 <https://github.com/pytorch/vision/tree/v0.17.1>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `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/rocm6.3_ubuntu22.04_py3.9_pytorch_release_1.13.1/images/sha256-994424ed07a63113f79dd9aa72159124c00f5fbfe18127151e6658f7d0b6f821?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
+      - 22.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
+      - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `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/rocm6.3_ubuntu20.04_py3.9_pytorch_release_1.13.1/images/sha256-7b8139fe40a9aeb4bca3aecd15c22c1fa96e867d93479fa3a24fdeeeeafa1219?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
+      - 20.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
+      - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `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>`_
+
+Critical ROCm libraries for PyTorch
+================================================================================
+
+The functionality of PyTorch with ROCm is shaped by its underlying library
+dependencies. These critical ROCm components affect the capabilities,
+performance, and feature set available to developers.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+      - Used in
+    * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
+      - 1.1.0
+      - Enables faster execution of core operations like matrix multiplication
+        (GEMM), convolutions and transformations.
+      - Speeds up ``torch.permute``, ``torch.view``, ``torch.matmul``,
+        ``torch.mm``, ``torch.bmm``, ``torch.nn.Conv2d``, ``torch.nn.Conv3d``
+        and ``torch.nn.MultiheadAttention``. 
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
+      - 2.3.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations like matrix multiplication, matrix-vector products,
+        and tensor contractions. Utilized in both dense and batched linear
+        algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
+      - 0.10.0
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - It accelerates operations like ``torch.matmul``, ``torch.mm``, and the
+        matrix multiplications used in convolutional and linear layers.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`_
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+      - Supports operations like ``torch.sum``, ``torch.cumsum``, ``torch.sort``
+        and ``torch.topk``. Operations on sparse tensors or tensors with
+        irregular shapes often involve scanning, sorting, and filtering, which
+        hipCUB handles efficiently.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
+      - 1.0.17
+      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
+      - Used in functions like the ``torch.fft`` module.
+    * - `hipRAND <https://github.com/ROCm/hipRAND>`_
+      - 2.11.0
+      - Provides fast random number generation for GPUs.
+      - The ``torch.rand``, ``torch.randn`` and stochastic layers like 
+        ``torch.nn.Dropout``.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
+      - 2.3.0
+      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
+        singular value decompositions (SVD).
+      - Supports functions like ``torch.linalg.solve``,
+        ``torch.linalg.eig``, and ``torch.linalg.svd``.
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
+      - 3.1.2
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
+      - 0.2.2
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipTensor <https://github.com/ROCm/hipTensor>`_
+      - 1.4.0
+      - Optimizes for high-performance tensor operations, such as contractions.
+      - Accelerates tensor algebra, especially in deep learning and scientific
+        computing.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
+      - 3.3.0
+      - Optimizes deep learning primitives such as convolutions, pooling,
+        normalization, and activation functions.
+      - Speeds up convolutional neural networks (CNNs), recurrent neural
+        networks (RNNs), and other layers. Used in operations like
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`_
+      - 2.11.0
+      - Add graph-level optimizations, ONNX models and mixed precision support
+        and enable Ahead-of-Time (AOT) Compilation.
+      - Speeds up inference models and executes ONNX models for
+        compatibility with other frameworks.
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIVisionX <https://github.com/ROCm/MIVisionX>`_
+      - 3.1.0
+      - Optimizes acceleration for computer vision and AI workloads like
+        preprocessing, augmentation, and inferencing.
+      - Faster data preprocessing and augmentation pipelines for datasets like
+        ImageNet or COCO and easy to integrate into PyTorch's ``torch.utils.data``
+        and ``torchvision`` workflows.
+    * - `rocAL <https://github.com/ROCm/rocAL>`_
+      - 2.1.0
+      - Accelerates the data pipeline by offloading intensive preprocessing and
+        augmentation tasks. rocAL is part of MIVisionX.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `RCCL <https://github.com/ROCm/rccl>`_
+      - 2.21.5
+      - Optimizes for multi-GPU communication for operations like AllReduce and
+        Broadcast.
+      - Distributed data parallel training (``torch.nn.parallel.DistributedDataParallel``).
+        Handles communication in multi-GPU setups.
+    * - `rocDecode <https://github.com/ROCm/rocDecode>`_
+      - 0.8.0
+      - Provide hardware-accelerated data decoding capabilities, particularly
+        for image, video, and other dataset formats.
+      - Can be integrated in ``torch.utils.data``, ``torchvision.transforms``
+        and ``torch.distributed``.
+    * - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
+      - 0.6.0
+      - Provide hardware-accelerated JPEG image decoding and encoding.
+      - GPU accelerated ``torchvision.io.decode_jpeg`` and
+        ``torchvision.io.encode_jpeg`` and can be integrated in
+        ``torch.utils.data`` and ``torchvision``.
+    * - `RPP <https://github.com/ROCm/RPP>`_
+      - 1.9.1
+      - Speed up data augmentation, transformation, and other preprocessing step.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+      - Utilized in backend operations for tensor computations requiring
+        parallel processing.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
+      - 1.6.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Linear layers (``torch.nn.Linear``), convolutional layers
+        (``torch.nn.Conv2d``), attention layers, general tensor operations that
+        involve matrix products, such as ``torch.matmul``, ``torch.bmm``, and
+        more.
+
+Supported and unsupported features
+================================================================================
+
+The following section maps GPU-accelerated PyTorch features to their supported
+ROCm and PyTorch versions.
+
+torch
+--------------------------------------------------------------------------------
+
+`torch <https://pytorch.org/docs/stable/index.html>`_ is the central module of
+PyTorch, providing data structures for multi-dimensional tensors and
+implementing mathematical operations on them. It also includes utilities for
+efficient serialization of tensors and arbitrary data types, along with various
+other tools.
+
+Tensor data types
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The data type of a tensor is specified using the ``dtype`` attribute or argument, and PyTorch supports a wide range of data types for different use cases.
+
+The following table lists `torch.Tensor <https://pytorch.org/docs/stable/tensors.html>`_'s single data types:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``torch.float8_e4m3fn``
+      - 8-bit floating point, e4m3
+      - 2.3
+      - 5.5
+    * - ``torch.float8_e5m2``
+      - 8-bit floating point, e5m2
+      - 2.3
+      - 5.5
+    * - ``torch.float16`` or ``torch.half``
+      - 16-bit floating point
+      - 0.1.6
+      - 2.0
+    * - ``torch.bfloat16``
+      - 16-bit floating point
+      - 1.6
+      - 2.6
+    * - ``torch.float32`` or ``torch.float``
+      - 32-bit floating point
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.float64`` or ``torch.double``
+      - 64-bit floating point
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.complex32`` or ``torch.chalf``
+      - PyTorch provides native support for 32-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.complex64`` or ``torch.cfloat``
+      - PyTorch provides native support for 64-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.complex128`` or ``torch.cdouble``
+      - PyTorch provides native support for 128-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.uint8``
+      - 8-bit integer (unsigned)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.uint16``
+      - 16-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.uint32``
+      - 32-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.uint64``
+      - 32-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.int8``
+      - 8-bit integer (signed)
+      - 1.12
+      - 5.0
+    * - ``torch.int16`` or ``torch.short``
+      - 16-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.int32`` or ``torch.int``
+      - 32-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.int64`` or ``torch.long``
+      - 64-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.bool``
+      - Boolean
+      - 1.2
+      - 2.0
+    * - ``torch.quint8``
+      - Quantized 8-bit integer (unsigned)
+      - 1.8
+      - 5.0
+    * - ``torch.qint8``
+      - Quantized 8-bit integer (signed)
+      - 1.8
+      - 5.0
+    * - ``torch.qint32``
+      - Quantized 32-bit integer (signed)
+      - 1.8
+      - 5.0
+    * - ``torch.quint4x2``
+      - Quantized 4-bit integer (unsigned)
+      - 1.8
+      - 5.0
+
+.. note::
+
+  Unsigned types aside from ``uint8`` are currently only have limited support in
+  eager mode (they primarily exist to assist usage with ``torch.compile``).
+
+  The :doc:`ROCm precision support page <rocm:reference/precision-support>`
+  collected the native HW support of different data types.
+
+torch.cuda
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``torch.cuda`` in PyTorch is a module that provides utilities and functions for
+managing and utilizing AMD and NVIDIA GPUs. It enables GPU-accelerated
+computations, memory management, and efficient execution of tensor operations,
+leveraging ROCm and CUDA as the underlying frameworks.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - Device management
+      - Utilities for managing and interacting with GPUs.
+      - 0.4.0
+      - 3.8
+    * - Tensor operations on GPU
+      - Perform tensor operations such as addition and matrix multiplications on
+        the GPU.
+      - 0.4.0
+      - 3.8
+    * - Streams and events
+      - Streams allow overlapping computation and communication for optimized
+        performance, events enable synchronization.
+      - 1.6.0
+      - 3.8
+    * - Memory management
+      - Functions to manage and inspect memory usage like
+        ``torch.cuda.memory_allocated()``, ``torch.cuda.max_memory_allocated()``,
+        ``torch.cuda.memory_reserved()`` and ``torch.cuda.empty_cache()``.
+      - 0.3.0
+      - 1.9.2
+    * - Running process lists of memory management
+      - Return a human-readable printout of the running processes and their GPU
+        memory use for a given device with functions like 
+        ``torch.cuda.memory_stats()`` and ``torch.cuda.memory_summary()``.
+      - 1.8.0
+      - 4.0
+    * - Communication collectives
+      - A set of APIs that enable efficient communication between multiple GPUs,
+        allowing for distributed computing and data parallelism.
+      - 1.9.0
+      - 5.0
+    * - ``torch.cuda.CUDAGraph``
+      - Graphs capture sequences of GPU operations to minimize kernel launch
+        overhead and improve performance.
+      - 1.10.0
+      - 5.3
+    * - TunableOp
+      - A mechanism that allows certain operations to be more flexible and
+        optimized for performance. It enables automatic tuning of kernel
+        configurations and other settings to achieve the best possible
+        performance based on the specific hardware (GPU) and workload.
+      - 2.0
+      - 5.4
+    * - NVIDIA Tools Extension (NVTX)
+      - Integration with NVTX for profiling and debugging GPU performance using
+        NVIDIA's Nsight tools.
+      - 1.8.0
+      - ❌
+    * - Lazy loading NVRTC
+      - Delays JIT compilation with NVRTC until the code is explicitly needed.
+      - 1.13.0
+      - ❌
+    * - Jiterator (beta)
+      - Jiterator allows asynchronous data streaming into computation streams
+        during training loops.
+      - 1.13.0
+      - 5.2
+
+.. Need to validate and extend.
+
+torch.backends.cuda
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``torch.backends.cuda`` is a PyTorch module that provides configuration options
+and flags to control the behavior of CUDA or ROCm operations. It is part of the
+PyTorch backend configuration system, which allows users to fine-tune how
+PyTorch interacts with the CUDA or ROCm environment.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``cufft_plan_cache``
+      - Manages caching of GPU FFT plans to optimize repeated FFT computations.
+      - 1.7.0
+      - 5.0
+    * - ``matmul.allow_tf32``
+      - Enables or disables the use of TensorFloat-32 (TF32) precision for
+        faster matrix multiplications on GPUs with Tensor Cores.
+      - 1.10.0
+      - ❌
+    * - ``matmul.allow_fp16_reduced_precision_reduction``
+      - Reduced precision reductions (e.g., with fp16 accumulation type) are
+        allowed with fp16 GEMMs.
+      - 2.0
+      - ❌
+    * - ``matmul.allow_bf16_reduced_precision_reduction``
+      - Reduced precision reductions are allowed with bf16 GEMMs.
+      - 2.0
+      - ❌
+    * - ``enable_cudnn_sdp``
+      - Globally enables cuDNN SDPA's kernels within SDPA.
+      - 2.0
+      - ❌
+    * - ``enable_flash_sdp``
+      - Globally enables or disables FlashAttention for SDPA.
+      - 2.1
+      - ❌
+    * - ``enable_mem_efficient_sdp``
+      - Globally enables or disables Memory-Efficient Attention for SDPA.
+      - 2.1
+      - ❌
+    * - ``enable_math_sdp``
+      - Globally enables or disables the PyTorch C++ implementation within SDPA.
+      - 2.1
+      - ❌
+
+.. Need to validate and extend.
+
+torch.backends.cudnn
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Supported ``torch`` options:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``allow_tf32``
+      - TensorFloat-32 tensor cores may be used in cuDNN convolutions on NVIDIA
+        Ampere or newer GPUs.
+      - 1.12.0
+      - ❌
+    * - ``deterministic``
+      - A bool that, if True, causes cuDNN to only use deterministic
+        convolution algorithms.
+      - 1.12.0
+      - 6.0
+
+Automatic mixed precision: torch.amp
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+PyTorch that automates the process of using both 16-bit (half-precision,
+float16) and 32-bit (single-precision, float32) floating-point types in model
+training and inference.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - Autocasting
+      - Instances of autocast serve as context managers or decorators that allow
+        regions of your script to run in mixed precision.
+      - 1.9
+      - 2.5
+    * - Gradient scaling
+      - To prevent underflow, “gradient scaling” multiplies the network’s
+        loss(es) by a scale factor and invokes a backward pass on the scaled
+        loss(es). Gradients flowing backward through the network are then
+        scaled by the same factor. In other words, gradient values have a
+        larger magnitude, so they don’t flush to zero.
+      - 1.9
+      - 2.5
+    * - CUDA op-specific behavior
+      - These ops always go through autocasting whether they are invoked as part
+        of a ``torch.nn.Module``, as a function, or as a ``torch.Tensor`` method. If
+        functions are exposed in multiple namespaces, they go through
+        autocasting regardless of the namespace.
+      - 1.9
+      - 2.5
+
+Distributed library features
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The PyTorch distributed library includes a collective of parallelism modules, a
+communications layer, and infrastructure for launching and debugging large
+training jobs. See :ref:`rocm-for-ai-pytorch-distributed` for more information.
+
+The Distributed Library feature in PyTorch provides tools and APIs for building
+and running distributed machine learning workflows. It allows training models
+across multiple processes, GPUs, or nodes in a cluster, enabling efficient use
+of computational resources and scalability for large-scale tasks.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - TensorPipe
+      - TensorPipe is a point-to-point communication library integrated into
+        PyTorch for distributed training. It is designed to handle tensor data
+        transfers efficiently between different processes or devices, including
+        those on separate machines.
+      - 1.8
+      - 5.4
+    * - Gloo
+      - Gloo is designed for multi-machine and multi-GPU setups, enabling
+        efficient communication and synchronization between processes. Gloo is
+        one of the default backends for PyTorch's Distributed Data Parallel
+        (DDP) and RPC frameworks, alongside other backends like NCCL and MPI.
+      - 1.0
+      - 2.0
+
+torch.compiler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``torch.compiler`` (AOT Autograd)
+      - Autograd captures not only the user-level code, but also backpropagation,
+        which results in capturing the backwards pass “ahead-of-time”. This
+        enables acceleration of both forwards and backwards pass using
+        ``TorchInductor``.
+      - 2.0
+      - 5.3
+    * - ``torch.compiler`` (TorchInductor)
+      - The default ``torch.compile`` deep learning compiler that generates fast
+        code for multiple accelerators and backends. You need to use a backend
+        compiler to make speedups through ``torch.compile`` possible. For AMD,
+        NVIDIA, and Intel GPUs, it leverages OpenAI Triton as the key building block.
+      - 2.0
+      - 5.3
+
+torchaudio
+--------------------------------------------------------------------------------
+
+The `torchaudio <https://pytorch.org/audio/stable/index.html>`_ library provides
+utilities for processing audio data in PyTorch, such as audio loading,
+transformations, and feature extraction.
+
+To ensure GPU-acceleration with ``torchaudio.transforms``, you need to move audio
+data (waveform tensor) explicitly to GPU using ``.to('cuda')``.
+
+The following ``torchaudio`` features are GPU-accelerated.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since torchaudio version
+      - Since ROCm
+    * - ``torchaudio.transforms.Spectrogram``
+      - Generate spectrogram of an input waveform using STFT.
+      - 0.6.0
+      - 4.5
+    * - ``torchaudio.transforms.MelSpectrogram``
+      - Generate the mel-scale spectrogram of raw audio signals.
+      - 0.9.0
+      - 4.5
+    * - ``torchaudio.transforms.MFCC``
+      - Extract of MFCC features.
+      - 0.9.0
+      - 4.5
+    * - ``torchaudio.transforms.Resample``
+      - Resample a signal from one frequency to another
+      - 0.9.0
+      - 4.5
+
+torchvision
+--------------------------------------------------------------------------------
+
+The `torchvision <https://pytorch.org/vision/stable/index.html>`_ library
+provide datasets, model architectures, and common image transformations for
+computer vision.
+
+The following ``torchvision`` features are GPU-accelerated.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since torchvision version
+      - Since ROCm
+    * - ``torchvision.transforms.functional``
+      - Provides GPU-compatible transformations for image preprocessing like
+        resize, normalize, rotate and crop.
+      - 0.2.0
+      - 4.0
+    * - ``torchvision.ops``
+      - GPU-accelerated operations for object detection and segmentation tasks.
+        ``torchvision.ops.roi_align``, ``torchvision.ops.nms`` and
+        ``box_convert``.
+      - 0.6.0
+      - 3.3
+    * - ``torchvision.models`` with ``.to('cuda')``
+      - ``torchvision`` provides several pre-trained models (ResNet, Faster
+        R-CNN, Mask R-CNN, ...) that can run on CUDA for faster inference and
+        training.
+      - 0.1.6
+      - 2.x
+    * - ``torchvision.io``
+      - Video decoding and frame extraction using GPU acceleration with NVIDIA’s
+        NVDEC and nvJPEG (rocJPEG) on CUDA-enabled GPUs.
+      - 0.4.0
+      - 6.3
+
+torchtext
+--------------------------------------------------------------------------------
+
+The `torchtext <https://pytorch.org/text/stable/index.html>`_ library provides
+utilities for processing and working with text data in PyTorch, including
+tokenization, vocabulary management, and text embeddings. torchtext supports
+preprocessing pipelines and integration with PyTorch models, simplifying the
+implementation of natural language processing (NLP) tasks.
+
+To leverage GPU acceleration in torchtext, you need to move tensors
+explicitly to the GPU using ``.to('cuda')``.
+
+* torchtext does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+torchtune
+--------------------------------------------------------------------------------
+
+The `torchtune <https://pytorch.org/torchtune/stable/index.html>`_ library for
+authoring, fine-tuning and experimenting with LLMs.
+
+* Usage: It works out-of-the-box, enabling developers to fine-tune ROCm PyTorch solutions.
+
+* Only official release exists.
+
+torchserve
+--------------------------------------------------------------------------------
+
+The `torchserve <https://pytorch.org/torchserve/>`_ is a PyTorch domain library
+for common sparsity and parallelism primitives needed for large-scale recommender
+systems.
+
+* torchtext does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+torchrec
+--------------------------------------------------------------------------------
+
+The `torchrec <https://pytorch.org/torchrec/>`_ is a PyTorch domain library for
+common sparsity and parallelism primitives needed for large-scale recommender
+systems.
+
+* torchrec does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+Unsupported PyTorch features
+----------------------------
+
+The following are GPU-accelerated PyTorch features not currently supported by ROCm.
+
+.. list-table::
+    :widths: 30, 60, 10
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+    * - APEX batch norm
+      - Use APEX batch norm instead of PyTorch batch norm.
+      - 1.6.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_tf32``
+      - A bool that controls whether TensorFloat-32 tensor cores may be used in
+        matrix multiplications.
+      - 1.7
+    * - ``torch.cuda`` / NVIDIA Tools Extension (NVTX)
+      - Integration with NVTX for profiling and debugging GPU performance using
+        NVIDIA's Nsight tools.
+      - 1.7.0
+    * - ``torch.cuda`` / Lazy loading NVRTC
+      - Delays JIT compilation with NVRTC until the code is explicitly needed.
+      - 1.8.0
+    * - ``torch-tensorrt``
+      - Integrate TensorRT library for optimizing and deploying PyTorch models.
+        ROCm does not have equialent library for TensorRT.
+      - 1.9.0
+    * - ``torch.backends`` / ``cudnn.allow_tf32``
+      - TensorFloat-32 tensor cores may be used in cuDNN convolutions.
+      - 1.10.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_fp16_reduced_precision_reduction``
+      - Reduced precision reductions with fp16 accumulation type are
+        allowed with fp16 GEMMs.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_bf16_reduced_precision_reduction``
+      - Reduced precision reductions are allowed with bf16 GEMMs.
+      - 2.0
+    * - ``torch.nn.functional`` / ``scaled_dot_product_attention`` 
+      - Flash attention backend for SDPA to accelerate attention computation in
+        transformer-based models.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``enable_cudnn_sdp``
+      - Globally enables cuDNN SDPA's kernels within SDPA.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``enable_flash_sdp``
+      - Globally enables or disables FlashAttention for SDPA.
+      - 2.1
+    * - ``torch.backends.cuda`` / ``enable_mem_efficient_sdp``
+      - Globally enables or disables Memory-Efficient Attention for SDPA.
+      - 2.1
+    * - ``torch.backends.cuda`` / ``enable_math_sdp``
+      - Globally enables or disables the PyTorch C++ implementation within SDPA.
+      - 2.1
+    * - Dynamic parallelism
+      - PyTorch itself does not directly expose dynamic parallelism as a core
+        feature. Dynamic parallelism allow GPU threads to launch additional
+        threads which can be reached using custom operations via the
+        ``torch.utils.cpp_extension`` module.
+      - Not a core feature
+    * - Unified memory support in PyTorch
+      - Unified Memory is not directly exposed in PyTorch's core API, it can be
+        utilized effectively through custom CUDA extensions or advanced
+        workflows.
+      - Not a core feature
+
+Use cases and recommendations
+================================================================================
+
+* :doc:`Using ROCm for AI: training a model </how-to/rocm-for-ai/train-a-model>` provides
+  guidance on how to leverage the ROCm platform for training AI models. It covers the steps, tools, and best practices
+  for optimizing training workflows on AMD GPUs using PyTorch features.
+
+* :doc:`Single-GPU fine-tuning and inference </how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference>`
+  describes and demonstrates how to use the ROCm platform for the fine-tuning and inference of
+  machine learning models, particularly large language models (LLMs), on systems with a single AMD
+  Instinct MI300X accelerator. This page provides a detailed guide for setting up, optimizing, and
+  executing fine-tuning and inference workflows in such environments.
+
+* :doc:`Multi-GPU fine-tuning and inference optimization </how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference>`
+  describes and demonstrates the fine-tuning and inference of machine learning models on systems
+  with multi MI300X accelerators.
+
+* The :doc:`Instinct MI300X workload optimization guide </how-to/tuning-guides/mi300x/workload>` provides detailed
+  guidance on optimizing workloads for the AMD Instinct MI300X accelerator using ROCm. This guide is aimed at helping
+  users achieve optimal performance for deep learning and other high-performance computing tasks on the MI300X
+  accelerator.
+
+* The :doc:`Inception with PyTorch documentation </conceptual/ai-pytorch-inception>`
+  describes how PyTorch integrates with ROCm for AI workloads It outlines the use of PyTorch on the ROCm platform and
+  focuses on how to efficiently leverage AMD GPU hardware for training and inference tasks in AI applications.
+
+For more use cases and recommendations, see `ROCm PyTorch blog posts <https://rocm.blogs.amd.com/blog/tag/pytorch.html>`_

docs/how-to/rocm-for-ai/fine-tuning/index.rst

@@ -16,6 +16,9 @@ Throughout the following topics, this guide discusses the goals and :ref:`challe
 model <fine-tuning-llms-concept-challenge>` like Llama 2. In the
 sections that follow, you'll find practical guides on libraries and tools to accelerate your fine-tuning.
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 - :doc:`Conceptual overview of fine-tuning LLMs <overview>`
 
 - :doc:`Fine-tuning and inference <fine-tuning-and-inference>` using a

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

@@ -12,6 +12,9 @@ You can use ROCm to perform distributed training, which enables you to train mod
  
 Overall, ROCm can be used to improve the performance and efficiency of your AI applications. With its training, fine-tuning, and inference support, ROCm provides a complete solution for optimizing AI workflows and achieving the optimum results possible on AMD GPUs. 
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 In this guide, you'll learn how to use ROCm for AI:
 
 - :doc:`Training <training/index>`

docs/how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst

@@ -277,7 +277,7 @@ Installing FBGEMM_GPU
 Installing FBGEMM_GPU consists of the following steps:
 
 *  Set up an isolated Miniconda environment
-*  Install ROCm using Docker or the :doc:`package manager <rocm-install-on-linux:install/native-install/index>`
+*  Install ROCm using Docker or the :doc:`package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
 *  Install the nightly `PyTorch <https://pytorch.org/>`_ build
 *  Complete the pre-build and build tasks
   

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

@@ -11,6 +11,9 @@ Understanding the ROCm™ software platform’s architecture and capabilities is
 
 Throughout the following topics, this section provides a comprehensive guide to setting up and deploying AI inference on AMD GPUs. This includes instructions on how to install ROCm, how to use Hugging Face Transformers to manage pre-trained models for natural language processing (NLP) tasks, how to validate vLLM on AMD Instinct™ MI300X accelerators and illustrate how to deploy trained models in production environments. 
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 - :doc:`Installing ROCm and machine learning frameworks <install>`
 
 - :doc:`Running models from Hugging Face <hugging-face-models>`

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

@@ -26,7 +26,7 @@ If you’re using a Radeon GPU for graphics-accelerated applications, refer to t
 
 ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install/install-overview>`:
 
-* :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/native-install/index>`
+* :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/amdgpu-install>`
 

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

@@ -10,49 +10,22 @@ LLM inference performance validation on AMD Instinct MI300X
 .. _vllm-benchmark-unified-docker:
 
 The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
-a prebuilt, optimized environment designed for validating large language model
-(LLM) inference performance on the AMD Instinct™ MI300X accelerator. This
-ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
-MI300X accelerator and includes the following components:
+a prebuilt, optimized environment for validating large language model (LLM)
+inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
+Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
+accelerator and includes the following components:
 
-* `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_
+* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
 
-* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_
+* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
 
-* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
-
-* Tuning files (in CSV format)
+* `PyTorch 2.7.0 (2.7.0a0+git3a58512) <https://github.com/pytorch/pytorch>`_
 
 With this Docker image, you can quickly validate the expected inference
-performance numbers on the MI300X accelerator. This topic also provides tips on
-optimizing performance with popular AI models.
-
-.. hlist::
-   :columns: 6
-
-   * Llama 3.1 8B
-
-   * Llama 3.1 70B
-
-   * Llama 3.1 405B
-
-   * Llama 2 7B
-
-   * Llama 2 70B
-
-   * Mixtral 8x7B
-
-   * Mixtral 8x22B
-
-   * Mixtral 7B
-
-   * Qwen2 7B
-
-   * Qwen2 72B
-
-   * JAIS 13B
-
-   * JAIS 30B
+performance numbers for the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models. For more information, see the lists of
+:ref:`available models for MAD-integrated benchmarking <vllm-benchmark-mad-models>`
+and :ref:`standalone benchmarking <vllm-benchmark-standalone-options>`.
 
 .. _vllm-benchmark-vllm:
 
@@ -91,9 +64,9 @@ MI300X accelerator with the prebuilt vLLM Docker image.
 
    .. code-block:: shell
 
-      docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
-Once setup is complete, you can choose between two options to reproduce the
+Once the setup is complete, choose between two options to reproduce the
 benchmark results:
 
 -  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
@@ -130,45 +103,89 @@ Although the following models are preconfigured to collect latency and
 throughput performance data, you can also change the benchmarking parameters.
 Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
 
+.. _vllm-benchmark-mad-models:
+
 Available models
 ----------------
 
-.. hlist::
-   :columns: 3
+.. list-table::
+   :header-rows: 1
+   :widths: 2, 3
 
-   * ``pyt_vllm_llama-3.1-8b``
+   * - Model name
+     - Tag
 
-   * ``pyt_vllm_llama-3.1-70b``
+   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+     - ``pyt_vllm_llama-3.1-8b``
 
-   * ``pyt_vllm_llama-3.1-405b``
+   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-70b``
 
-   * ``pyt_vllm_llama-2-7b``
+   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-405b``
 
-   * ``pyt_vllm_llama-2-70b``
+   * - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
+     - ``pyt_vllm_llama-3.2-11b-vision-instruct``
 
-   * ``pyt_vllm_mixtral-8x7b``
+   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+     - ``pyt_vllm_llama-2-7b``
 
-   * ``pyt_vllm_mixtral-8x22b``
+   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+     - ``pyt_vllm_llama-2-70b``
 
-   * ``pyt_vllm_mistral-7b``
+   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x7b``
 
-   * ``pyt_vllm_qwen2-7b``
+   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x22b``
 
-   * ``pyt_vllm_qwen2-72b``
+   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+     - ``pyt_vllm_mistral-7b``
 
-   * ``pyt_vllm_jais-13b``
+   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+     - ``pyt_vllm_qwen2-7b``
 
-   * ``pyt_vllm_jais-30b``
+   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+     - ``pyt_vllm_qwen2-72b``
 
-   * ``pyt_vllm_llama-3.1-8b_fp8``
+   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+     - ``pyt_vllm_jais-13b``
 
-   * ``pyt_vllm_llama-3.1-70b_fp8``
+   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
+     - ``pyt_vllm_jais-30b``
 
-   * ``pyt_vllm_llama-3.1-405b_fp8``
+   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+     - ``pyt_vllm_dbrx-instruct``
 
-   * ``pyt_vllm_mixtral-8x7b_fp8``
+   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+     - ``pyt_vllm_gemma-2-27b``
 
-   * ``pyt_vllm_mixtral-8x22b_fp8``
+   * - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
+     - ``pyt_vllm_c4ai-command-r-plus-08-2024``
+
+   * - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
+     - ``pyt_vllm_deepseek-moe-16b-chat``
+
+   * - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
+     - ``pyt_vllm_llama-3.1-70b_fp8``
+
+   * - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
+     - ``pyt_vllm_llama-3.1-405b_fp8``
+
+   * - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mixtral-8x7b_fp8``
+
+   * - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mixtral-8x22b_fp8``
+
+   * - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mistral-7b_fp8``
+
+   * - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
+     - ``pyt_vllm_dbrx_fp8``
+
+   * - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
+     - ``pyt_vllm_command-r-plus_fp8``
 
 .. _vllm-benchmark-standalone:
 
@@ -181,8 +198,8 @@ snippet.
 
 .. code-block::
 
-   docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
-   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.4 rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+   docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+   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 vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
 In the Docker container, clone the ROCm MAD repository and navigate to the
 benchmark scripts directory at ``~/MAD/scripts/vllm``.
@@ -224,8 +241,8 @@ See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
 
 .. _vllm-benchmark-standalone-options:
 
-Options
--------
+Options and available models
+----------------------------
 
 .. list-table::
    :header-rows: 1
@@ -248,72 +265,100 @@ Options
      - Measure both throughput and latency
 
    * - ``$model_repo``
-     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
-     - Llama 3.1 8B
+     - ``meta-llama/Llama-3.1-8B-Instruct``
+     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
 
    * - (``float16``)
-     - ``meta-llama/Meta-Llama-3.1-70B-Instruct``
-     - Llama 3.1 70B
+     - ``meta-llama/Llama-3.1-70B-Instruct``
+     - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
 
    * -
-     - ``meta-llama/Meta-Llama-3.1-405B-Instruct``
-     - Llama 3.1 405B
+     - ``meta-llama/Llama-3.1-405B-Instruct``
+     - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-3.2-11B-Vision-Instruct``
+     - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
 
    * -
      - ``meta-llama/Llama-2-7b-chat-hf``
-     - Llama 2 7B
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
 
    * -
      - ``meta-llama/Llama-2-70b-chat-hf``
-     - Llama 2 70B
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
 
    * -
      - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
-     - Mixtral 8x7B
+     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
 
    * -
      - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
-     - Mixtral 8x22B
+     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
 
    * -
      - ``mistralai/Mistral-7B-Instruct-v0.3``
-     - Mixtral 7B
+     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
 
    * -
      - ``Qwen/Qwen2-7B-Instruct``
-     - Qwen2 7B
+     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
 
    * -
      - ``Qwen/Qwen2-72B-Instruct``
-     - Qwen2 72B
+     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
 
    * -
      - ``core42/jais-13b-chat``
-     - JAIS 13B
+     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
 
    * -
      - ``core42/jais-30b-chat-v3``
-     - JAIS 30B
-
-   * - ``$model_repo``
-     - ``amd/Meta-Llama-3.1-8B-Instruct-FP8-KV``
-     - Llama 3.1 8B
-
-   * - (``float8``)
-     - ``amd/Meta-Llama-3.1-70B-Instruct-FP8-KV``
-     - Llama 3.1 70B
+     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
 
    * -
-     - ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
-     - Llama 3.1 405B
+     - ``databricks/dbrx-instruct``
+     - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+
+   * -
+     - ``google/gemma-2-27b``
+     - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+
+   * -
+     - ``CohereForAI/c4ai-command-r-plus-08-2024``
+     - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
+
+   * -
+     - ``deepseek-ai/deepseek-moe-16b-chat``
+     - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
+
+   * - ``$model_repo``
+     - ``amd/Llama-3.1-70B-Instruct-FP8-KV``
+     - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
+
+   * - (``float8``)
+     - ``amd/Llama-3.1-405B-Instruct-FP8-KV``
+     - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
 
    * -
      - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
-     - Mixtral 8x7B
+     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
 
    * -
      - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
-     - Mixtral 8x22B
+     - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/Mistral-7B-v0.1-FP8-KV``
+     - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/dbrx-instruct-FP8-KV``
+     - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
+
+   * -
+     - ``amd/c4ai-command-r-plus-FP8-KV``
+     - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
 
    * - ``$num_gpu``
      - 1 or 8
@@ -335,34 +380,34 @@ options and their descriptions.
 Example 1: latency benchmark
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
-Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+Use this command to benchmark the latency of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
 
 .. code-block::
 
-   ./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
-   ./vllm_benchmark_report.sh -s latency -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
+   ./vllm_benchmark_report.sh -s latency -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
 
 Find the latency reports at:
 
-- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
 
-- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_latency_report.csv``
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_latency_report.csv``
 
 Example 2: throughput benchmark
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+Use this command to benchmark the throughput of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
 
 .. code-block:: shell
 
-   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
-   ./vllm_benchmark_report.sh -s throughput -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
+   ./vllm_benchmark_report.sh -s throughput -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
 
 Find the throughput reports at:
 
-- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
 
-- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_throughput_report.csv``
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_throughput_report.csv``
 
 .. raw:: html
 
@@ -394,7 +439,7 @@ Further reading
   MI300X accelerators, see :doc:`../../system-optimization/mi300x`.
 
 - To learn how to run LLM models from Hugging Face or your own model, see
-  :doc:`Using ROCm for AI <../index>`.
+  :doc:`Running models from Hugging Face <hugging-face-models>`.
 
 - To learn how to optimize inference on LLMs, see
   :doc:`Inference optimization <../inference-optimization/index>`.
@@ -402,6 +447,32 @@ Further reading
 - To learn how to fine-tune LLMs, see
   :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
 
-- To compare with the previous version of the ROCm vLLM Docker image for performance validation, refer to
-  `LLM inference performance validation on AMD Instinct MI300X (ROCm 6.2.0) <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_.
+Previous versions
+=================
 
+This table lists previous versions of the ROCm vLLM Docker image for inference
+performance validation. For detailed information about available models for
+benchmarking, see the version-specific documentation.
+
+.. list-table::
+   :header-rows: 1
+   :stub-columns: 1
+
+   * - ROCm version
+     - vLLM version
+     - PyTorch version
+     - Resources
+
+   * - 6.2.1
+     - 0.6.4
+     - 2.5.0
+     - 
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4/images/sha256-ccbb74cc9e7adecb8f7bdab9555f7ac6fc73adb580836c2a35ca96ff471890d8>`_
+
+   * - 6.2.0
+     - 0.4.3
+     - 2.4.0
+     -
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50/images/sha256-9e4dd4788a794c3d346d7d0ba452ae5e92d39b8dfac438b2af8efdc7f15d22c0>`_

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

@@ -14,6 +14,9 @@ Training models on AMD GPUs with the ROCm™ software platform allows you to use
  
 The ROCm software platform makes it easier to train models on AMD GPUs while maintaining compatibility with existing code and tools. The platform also provides features like multi-GPU support, allowing for scaling and parallelization of model training across multiple GPUs to enhance performance. 
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 In this guide, you'll learn about:
 
 - :doc:`Training a model <train-a-model>`

docs/how-to/system-optimization/w6000-v620.md

@@ -12,7 +12,7 @@ myst:
 This chapter reviews system settings that are required to configure the system
 for ROCm virtualization on RDNA2-based AMD Radeon™ PRO GPUs. Installing ROCm on
 Bare Metal follows the routine ROCm
-{doc}`installation procedure<rocm-install-on-linux:install/native-install/index>`.
+{doc}`installation procedure<rocm-install-on-linux:install/install-methods/package-manager-index>`.
 
 To enable ROCm virtualization on V620, one has to setup Single Root I/O
 Virtualization (SR-IOV) in the BIOS via setting found in the following
@@ -166,4 +166,4 @@ First, assign GPU virtual function (VF) to VM using the following steps.
 Then start the VM.
 
 Finally install ROCm on the virtual machine (VM). For detailed instructions,
-refer to the {doc}`Linux install guide<rocm-install-on-linux:install/native-install/index>`.
+refer to the {doc}`Linux install guide<rocm-install-on-linux:install/install-methods/package-manager-index>`.

docs/index.md

@@ -38,6 +38,7 @@ ROCm documentation is organized into the following categories:
 :class-body: rocm-card-banner rocm-hue-12
 
 * [Use ROCm for AI](./how-to/rocm-for-ai/index.rst)
+* [AI tutorials](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/)
 * [Use ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
 * [System optimization](./how-to/system-optimization/index.rst)
 * [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)

docs/sphinx/_toc.yml.in

@@ -89,7 +89,10 @@ subtrees:
             title: Profile and debug
           - file: how-to/rocm-for-ai/inference-optimization/workload.rst
             title: Workload tuning
-  
+
+      - url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
+        title: AI tutorials
+
   - file: how-to/rocm-for-hpc/index.rst
     title: Use ROCm for HPC
   - file: how-to/system-optimization/index.rst
@@ -126,6 +129,7 @@ subtrees:
   - url: https://github.com/amd/rocm-examples
     title: ROCm examples
 
+
 - caption: Conceptual
   entries:
   - file: conceptual/gpu-arch.md

docs/sphinx/requirements.in

@@ -1,3 +1,3 @@
-rocm-docs-core==1.13.0
+rocm-docs-core==1.15.0
 sphinx-reredirects
 sphinx-sitemap

docs/sphinx/requirements.txt

@@ -8,27 +8,42 @@ accessible-pygments==0.0.5
     # via pydata-sphinx-theme
 alabaster==1.0.0
     # via sphinx
-babel==2.16.0
+asttokens==3.0.0
+    # via stack-data
+attrs==25.1.0
+    # via
+    #   jsonschema
+    #   jupyter-cache
+    #   referencing
+babel==2.17.0
     # via
     #   pydata-sphinx-theme
     #   sphinx
-beautifulsoup4==4.12.3
+beautifulsoup4==4.13.3
     # via pydata-sphinx-theme
 breathe==4.35.0
     # via rocm-docs-core
-certifi==2024.8.30
+certifi==2025.1.31
     # via requests
 cffi==1.17.1
     # via
     #   cryptography
     #   pynacl
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via requests
-click==8.1.7
-    # via sphinx-external-toc
-cryptography==43.0.3
+click==8.1.8
+    # via
+    #   jupyter-cache
+    #   sphinx-external-toc
+comm==0.2.2
+    # via ipykernel
+cryptography==44.0.1
     # via pyjwt
-deprecated==1.2.15
+debugpy==1.8.12
+    # via ipykernel
+decorator==5.1.1
+    # via ipython
+deprecated==1.2.18
     # via pygithub
 docutils==0.21.2
     # via
@@ -36,63 +51,151 @@ docutils==0.21.2
     #   myst-parser
     #   pydata-sphinx-theme
     #   sphinx
-fastjsonschema==2.20.0
-    # via rocm-docs-core
-gitdb==4.0.11
+exceptiongroup==1.2.2
+    # via ipython
+executing==2.2.0
+    # via stack-data
+fastjsonschema==2.21.1
+    # via
+    #   nbformat
+    #   rocm-docs-core
+gitdb==4.0.12
     # via gitpython
-gitpython==3.1.43
+gitpython==3.1.44
     # via rocm-docs-core
+greenlet==3.1.1
+    # via sqlalchemy
 idna==3.10
     # via requests
 imagesize==1.4.1
     # via sphinx
+importlib-metadata==8.6.1
+    # via
+    #   jupyter-cache
+    #   myst-nb
+ipykernel==6.29.5
+    # via myst-nb
+ipython==8.32.0
+    # via
+    #   ipykernel
+    #   myst-nb
+jedi==0.19.2
+    # via ipython
 jinja2==3.1.5
     # via
     #   myst-parser
     #   sphinx
+jsonschema==4.23.0
+    # via nbformat
+jsonschema-specifications==2024.10.1
+    # via jsonschema
+jupyter-cache==1.0.1
+    # via myst-nb
+jupyter-client==8.6.3
+    # via
+    #   ipykernel
+    #   nbclient
+jupyter-core==5.7.2
+    # via
+    #   ipykernel
+    #   jupyter-client
+    #   nbclient
+    #   nbformat
 markdown-it-py==3.0.0
     # via
     #   mdit-py-plugins
     #   myst-parser
 markupsafe==3.0.2
     # via jinja2
+matplotlib-inline==0.1.7
+    # via
+    #   ipykernel
+    #   ipython
 mdit-py-plugins==0.4.2
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-parser==4.0.0
+myst-nb==1.2.0
     # via rocm-docs-core
+myst-parser==4.0.0
+    # via myst-nb
+nbclient==0.10.2
+    # via
+    #   jupyter-cache
+    #   myst-nb
+nbformat==5.10.4
+    # via
+    #   jupyter-cache
+    #   myst-nb
+    #   nbclient
+nest-asyncio==1.6.0
+    # via ipykernel
 packaging==24.2
-    # via sphinx
+    # via
+    #   ipykernel
+    #   sphinx
+parso==0.8.4
+    # via jedi
+pexpect==4.9.0
+    # via ipython
+platformdirs==4.3.6
+    # via jupyter-core
+prompt-toolkit==3.0.50
+    # via ipython
+psutil==6.1.1
+    # via ipykernel
+ptyprocess==0.7.0
+    # via pexpect
+pure-eval==0.2.3
+    # via stack-data
 pycparser==2.22
     # via cffi
-pydata-sphinx-theme==0.16.0
+pydata-sphinx-theme==0.16.1
     # via
     #   rocm-docs-core
     #   sphinx-book-theme
 pygithub==2.5.0
     # via rocm-docs-core
-pygments==2.18.0
+pygments==2.19.1
     # via
     #   accessible-pygments
+    #   ipython
     #   pydata-sphinx-theme
     #   sphinx
-pyjwt[crypto]==2.10.0
+pyjwt[crypto]==2.10.1
     # via pygithub
 pynacl==1.5.0
     # via pygithub
+python-dateutil==2.9.0.post0
+    # via jupyter-client
 pyyaml==6.0.2
     # via
+    #   jupyter-cache
+    #   myst-nb
     #   myst-parser
     #   rocm-docs-core
     #   sphinx-external-toc
+pyzmq==26.2.1
+    # via
+    #   ipykernel
+    #   jupyter-client
+referencing==0.36.2
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
 requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.13.0
+rocm-docs-core==1.15.0
     # via -r requirements.in
-smmap==5.0.1
+rpds-py==0.22.3
+    # via
+    #   jsonschema
+    #   referencing
+six==1.17.0
+    # via python-dateutil
+smmap==5.0.2
     # via gitdb
 snowballstemmer==2.2.0
     # via sphinx
@@ -101,6 +204,7 @@ soupsieve==2.6
 sphinx==8.1.3
     # via
     #   breathe
+    #   myst-nb
     #   myst-parser
     #   pydata-sphinx-theme
     #   rocm-docs-core
@@ -119,7 +223,7 @@ sphinx-design==0.6.1
     # via rocm-docs-core
 sphinx-external-toc==1.0.1
     # via rocm-docs-core
-sphinx-notfound-page==1.0.4
+sphinx-notfound-page==1.1.0
     # via rocm-docs-core
 sphinx-reredirects==0.1.5
     # via -r requirements.in
@@ -137,15 +241,44 @@ sphinxcontrib-qthelp==2.0.0
     # via sphinx
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-tomli==2.1.0
+sqlalchemy==2.0.38
+    # via jupyter-cache
+stack-data==0.6.3
+    # via ipython
+tabulate==0.9.0
+    # via jupyter-cache
+tomli==2.2.1
     # via sphinx
+tornado==6.4.2
+    # via
+    #   ipykernel
+    #   jupyter-client
+traitlets==5.14.3
+    # via
+    #   comm
+    #   ipykernel
+    #   ipython
+    #   jupyter-client
+    #   jupyter-core
+    #   matplotlib-inline
+    #   nbclient
+    #   nbformat
 typing-extensions==4.12.2
     # via
+    #   beautifulsoup4
+    #   ipython
+    #   myst-nb
     #   pydata-sphinx-theme
     #   pygithub
-urllib3==2.2.3
+    #   referencing
+    #   sqlalchemy
+urllib3==2.3.0
     # via
     #   pygithub
     #   requests
-wrapt==1.17.0
+wcwidth==0.2.13
+    # via prompt-toolkit
+wrapt==1.17.2
     # via deprecated
+zipp==3.21.0
+    # via importlib-metadata

tools/rocm-build/build_composable_kernel.sh

@@ -68,85 +68,6 @@ set_address_sanitizer_off() {
     export LDFLAGS=""
 }
 
-build_miopen_ckProf() {
-    ENABLE_ADDRESS_SANITIZER=false
-    echo "Start Building Composable Kernel Profiler"
-    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
-       set_asan_env_vars
-       set_address_sanitizer_on
-    else
-       unset_asan_env_vars
-       set_address_sanitizer_off
-    fi
-
-    cd $COMPONENT_SRC
-    cd "$BUILD_DIR"
-    rm -rf *
-
-    architectures='gfx10 gfx11 gfx90 gfx94'
-    if [ -n "$GPU_ARCHS" ]; then
-        architectures=$(echo ${GPU_ARCHS} | awk -F';' '{for(i=1;i<=NF;i++) a[substr($i,1,5)]} END{for(i in a) printf i" "}')
-    fi
-
-    for arch in ${architectures}
-        do
-            if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
-                cmake -DBUILD_DEV=OFF \
-                    -DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
-                    -DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
-                    -DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
-                    -DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
-                    -DCMAKE_VERBOSE_MAKEFILE=1 \
-                    -DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
-                    -DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
-                    -DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-                    -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
-                    -DROCM_SYMLINK_LIBS=OFF \
-                    -DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-                    -DROCM_DISABLE_LDCONFIG=ON \
-                    -DROCM_PATH="${ROCM_PATH}" \
-                    -DCPACK_GENERATOR="${PKGTYPE^^}" \
-                    -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-                    -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
-                    ${LAUNCHER_FLAGS} \
-                    -DPROFILER_ONLY=ON \
-                    -DENABLE_ASAN_PACKAGING=true \
-                    -DGPU_ARCH="${arch}" \
-                    "$COMPONENT_SRC"
-            else
-                cmake -DBUILD_DEV=OFF \
-                    -DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}" \
-                    -DCMAKE_BUILD_TYPE=Release \
-                    -DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
-                    -DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
-                    -DCMAKE_VERBOSE_MAKEFILE=1 \
-                    -DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
-                    -DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
-                    -DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-                    -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
-                    -DROCM_SYMLINK_LIBS=OFF \
-                    -DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-                    -DROCM_DISABLE_LDCONFIG=ON \
-                    -DROCM_PATH="${ROCM_PATH}" \
-                    -DCPACK_GENERATOR="${PKGTYPE^^}" \
-                    -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-                    -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
-                    ${LAUNCHER_FLAGS} \
-                    -DPROFILER_ONLY=ON \
-                    -DGPU_ARCH="${arch}" \
-                    "$COMPONENT_SRC"
-            fi
-
-            cmake --build . -- -j${PROC} package
-            cp ./*ckprofiler*.${PKGTYPE} $PACKAGE_DIR
-            rm -rf *
-        done
-    rm -rf _CPack_Packages/ && find -name '*.o' -delete
-
-    echo "Finished building Composable Kernel"
-    show_build_cache_stats
-}
-
 clean_miopen_ck() {
     echo "Cleaning MIOpen-CK build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
     rm -rf "$BUILD_DIR" "$PACKAGE_DIR"

tools/rocm-build/build_lightning.sh

@@ -42,7 +42,6 @@ DEB_PATH="$(getDebPath $PROJ_NAME)"
 RPM_PATH="$(getRpmPath $PROJ_NAME)"
 INSTALL_PATH="${ROCM_INSTALL_PATH}/lib/llvm"
 LLVM_ROOT_LCL="${LLVM_ROOT}"
-ROCM_WHEEL_DIR="${BUILD_PATH}/_wheel"
 
 TARGET="all"
 MAKEOPTS="$DASH_JAY"
@@ -150,7 +149,6 @@ ENABLE_RUNTIMES="$ENABLE_RUNTIMES;libcxx;libcxxabi"
 BOOTSTRAPPING_BUILD_LIBCXX=1
 
 clean_lightning() {
-    rm -rf "$ROCM_WHEEL_DIR"
     rm -rf "$BUILD_PATH"
     rm -rf "$DEB_PATH"
     rm -rf "$RPM_PATH"
@@ -332,15 +330,6 @@ build_lightning() {
     echo "End Workaround for race condition"
     cmake --build . -- $MAKEOPTS
 
-    case "$DISTRO_ID" in
-    (rhel*|centos*)
-       RHEL_BUILD=1
-       ;;
-    (*)
-       RHEL_BUILD=0
-       ;;
-     esac
-
     if [ $SKIP_LIT_TESTS -eq 0 ]; then
         if [ $RHEL_BUILD -eq 1 ]; then
             cmake --build . -- $MAKEOPTS check-lld check-mlir
@@ -1158,9 +1147,4 @@ case $TARGET in
     (*) die "Invalid target $TARGET" ;;
 esac
 
-if [[ $WHEEL_PACKAGE == true ]]; then
-    echo "Wheel Package build started !!!!"
-    create_wheel_package
-fi
-
 echo "Operation complete"

tools/rocm-build/build_omniperf.sh

@@ -1,171 +0,0 @@
-#!/bin/bash
-
-source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
-
-printUsage() {
-    echo
-    echo "Usage: ${BASH_SOURCE##*/} [options ...]"
-    echo
-    echo "Options:"
-    echo "  -c,  --clean              Clean output and delete all intermediate work"
-    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
-    echo "  -p,  --package <type>     Specify packaging format"
-    echo "  -r,  --release            Make a release build instead of a debug build"
-    echo "  -a,  --address_sanitizer  Enable address sanitizer"
-    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
-                                      type referred to by pkg_type"
-    echo "  -w,  --wheel              Creates python wheel package of omniperf.
-                                      It needs to be used along with -r option"
-    echo "  -h,  --help               Prints this help"
-    echo
-    echo "Possible values for <type>:"
-    echo "  deb -> Debian format (default)"
-    echo "  rpm -> RPM format"
-    echo
-
-    return 0
-}
-
-API_NAME="omniperf"
-PROJ_NAME="$API_NAME"
-LIB_NAME="lib${API_NAME}"
-TARGET="build"
-MAKETARGET="deb"
-PACKAGE_ROOT="$(getPackageRoot)"
-PACKAGE_LIB="$(getLibPath)"
-BUILD_DIR="$(getBuildPath $API_NAME)"
-PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
-PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
-ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
-BUILD_TYPE="Debug"
-MAKE_OPTS="$DASH_JAY -C $BUILD_DIR"
-SHARED_LIBS="ON"
-CLEAN_OR_OUT=0;
-MAKETARGET="deb"
-PKGTYPE="deb"
-WHEEL_PACKAGE=false
-
-
-#parse the arguments
-VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,static,address_sanitizer,outdir:,package:,wheel -- "$@")
-eval set -- "$VALID_STR"
-
-while true ;
-do
-    case "$1" in
-        -h | --help)
-                printUsage ; exit 0;;
-        -c | --clean)
-                TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
-        -r | --release)
-                BUILD_TYPE="Release" ; shift ;;
-        -a | --address_sanitizer)
-                set_asan_env_vars
-                set_address_sanitizer_on ; shift ;;
-        -s | --static)
-                SHARED_LIBS="OFF" ; shift ;;
-        -o | --outdir)
-                TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
-        -p | --package)
-                MAKETARGET="$2" ; shift 2 ;;
-        -w | --wheel)
-                WHEEL_PACKAGE=true ; shift ;;
-        --)     shift; break;; # end delimiter
-        *)
-                echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
-    esac
-
-done
-
-RET_CONFLICT=1
-check_conflicting_options "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
-if [ $RET_CONFLICT -ge 30 ]; then
-   print_vars "$API_NAME" "$TARGET" "$BUILD_TYPE" "$SHARED_LIBS" "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
-   exit $RET_CONFLICT
-fi
-
-clean() {
-    echo "Cleaning $PROJ_NAME"
-    rm -rf "$ROCM_WHEEL_DIR"
-    rm -rf "$BUILD_DIR"
-    rm -rf "$PACKAGE_DEB"
-    rm -rf "$PACKAGE_RPM"
-    rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
-    rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
-}
-
-build() {
-    echo "Building $PROJ_NAME"
-    if [ "$DISTRO_ID" = centos-7 ]; then
-        echo "Skip make and uploading packages for Omniperf on Centos7 distro, due to python dependency"
-        exit 0
-    fi
-
-    if [ ! -d "$BUILD_DIR" ]; then
-        mkdir -p "$BUILD_DIR"
-        pushd "$BUILD_DIR" || exit
-
-        echo "ROCm CMake Params: $(rocm_cmake_params)"
-        echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
-
-        print_lib_type $SHARED_LIBS
-        cmake \
-            $(rocm_cmake_params) \
-            $(rocm_common_cmake_params) \
-            -DCHECK_PYTHON_DEPS=NO \
-            -DPYTHON_DEPS=${BUILD_DIR}/python-libs \
-            -DMOD_INSTALL_PATH=${BUILD_DIR}/modulefiles \
-            "$OMNIPERF_ROOT"
-    fi
-
-    make $MAKE_OPTS
-    make $MAKE_OPTS install
-    make $MAKE_OPTS package
-
-    copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
-    copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
-}
-
-create_wheel_package() {
-    echo "Creating Omniperf wheel package"
-
-    # Copy the setup.py generator to build folder
-    mkdir -p "$ROCM_WHEEL_DIR"
-    cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
-    cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
-    cd "$ROCM_WHEEL_DIR" || exit
-
-    # Currently only supports python3.6
-    ./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
-
-    # Copy the wheel created to RPM folder which will be uploaded to artifactory
-    copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
-}
-
-print_output_directory() {
-    case ${PKGTYPE} in
-        ("deb")
-            echo "${PACKAGE_DEB}";;
-        ("rpm")
-            echo "${PACKAGE_RPM}";;
-        (*)
-            echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
-    esac
-    exit
-}
-
-verifyEnvSetup
-
-case "$TARGET" in
-    (clean) clean ;;
-    (build) build ;;
-    (outdir) print_output_directory ;;
-    (*) die "Invalid target $TARGET" ;;
-esac
-
-if [[ $WHEEL_PACKAGE == true ]]; then
-    echo "Wheel Package build started !!!!"
-    create_wheel_package
-fi
-
-echo "Operation complete"

tools/rocm-build/build_omnitrace.sh

@@ -1,191 +0,0 @@
-#!/bin/bash
-
-source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
-
-printUsage() {
-    echo
-    echo "Usage: ${BASH_SOURCE##*/} [options ...]"
-    echo
-    echo "Options:"
-    echo "  -c,  --clean              Clean output and delete all intermediate work"
-    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
-    echo "  -p,  --package <type>     Specify packaging format"
-    echo "  -r,  --release            Make a release build instead of a debug build"
-    echo "  -a,  --address_sanitizer  Enable address sanitizer"
-    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
-                                      type referred to by pkg_type"
-    echo "  -w,  --wheel              Creates python wheel package of omnitrace.
-                                      It needs to be used along with -r option"
-    echo "  -h,  --help               Prints this help"
-    echo
-    echo "Possible values for <type>:"
-    echo "  deb -> Debian format (default)"
-    echo "  rpm -> RPM format"
-    echo
-
-    return 0
-}
-
-API_NAME="omnitrace"
-PROJ_NAME="$API_NAME"
-LIB_NAME="lib${API_NAME}"
-TARGET="build"
-MAKETARGET="deb"
-PACKAGE_ROOT="$(getPackageRoot)"
-PACKAGE_LIB="$(getLibPath)"
-BUILD_DIR="$(getBuildPath $API_NAME)"
-PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
-PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
-BUILD_TYPE="Debug"
-MAKE_OPTS="-j 8"
-SHARED_LIBS="ON"
-CLEAN_OR_OUT=0
-MAKETARGET="deb"
-PKGTYPE="deb"
-ASAN=0
-
-#parse the arguments
-VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,address_sanitizer,static,outdir:,package:,wheel -- "$@")
-eval set -- "$VALID_STR"
-
-while true; do
-    case "$1" in
-    -h | --help)
-        printUsage
-        exit 0
-        ;;
-    -c | --clean)
-        TARGET="clean"
-        ((CLEAN_OR_OUT |= 1))
-        shift
-        ;;
-    -r | --release)
-        BUILD_TYPE="RelWithDebInfo"
-        shift
-        ;;
-    -a | --address_sanitizer)
-        ack_and_ignore_asan
-
-        ASAN=1
-        shift
-        ;;
-    -s | --static)
-        SHARED_LIBS="OFF"
-        shift
-        ;;
-    -o | --outdir)
-        TARGET="outdir"
-        PKGTYPE=$2
-        ((CLEAN_OR_OUT |= 2))
-        shift 2
-        ;;
-    -p | --package)
-        MAKETARGET="$2"
-        shift 2
-        ;;
-    -w | --wheel)
-	   echo "omnitrace: wheel build option accepted and ignored"
-       shift
-       ;;
-    --)
-        shift
-        break
-        ;;
-    *)
-        echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
-        exit 20
-        ;;
-    esac
-
-done
-
-RET_CONFLICT=1
-check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
-if [ $RET_CONFLICT -ge 30 ]; then
-    print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
-    exit $RET_CONFLICT
-fi
-
-clean() {
-    echo "Cleaning $PROJ_NAME"
-    rm -rf "$BUILD_DIR"
-    rm -rf "$PACKAGE_DEB"
-    rm -rf "$PACKAGE_RPM"
-    rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
-    rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
-}
-
-build_omnitrace() {
-    echo "Building $PROJ_NAME"
-    if [ "$DISTRO_ID" = "mariner-2.0" ] || [ "$DISTRO_ID" = "ubuntu-24.04" ] || [ "$DISTRO_ID" = "azurelinux-3.0" ]; then
-        echo "Skip make and uploading packages for Omnitrace on \"${DISTRO_ID}\" distro"
-        exit 0
-    fi
-
-    if [ $ASAN == 1 ]; then
-        echo "Skip make and uploading packages for Omnitrace on ASAN build"
-        exit 0
-    fi
-    if [ ! -d "$BUILD_DIR" ]; then
-        mkdir -p "$BUILD_DIR"
-        echo "Created build directory: $BUILD_DIR"
-    fi
-
-    echo "Build directory: $BUILD_DIR"
-    pushd "$BUILD_DIR" || exit
-    print_lib_type $SHARED_LIBS
-
-    echo "ROCm CMake Params: $(rocm_cmake_params)"
-    echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
-
-
-    if [ $ASAN == 1 ]; then
-        echo "Address Sanitizer path"
-
-    else
-        cmake \
-            $(rocm_cmake_params) \
-            $(rocm_common_cmake_params) \
-            -DOMNITRACE_BUILD_{LIBUNWIND,DYNINST}=ON \
-            -DDYNINST_BUILD_{TBB,BOOST,ELFUTILS,LIBIBERTY}=ON \
-            "$OMNITRACE_ROOT"
-    fi
-
-
-    popd || exit
-
-    echo "Make Options: $MAKE_OPTS"
-    cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
-    cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
-    cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
-
-    copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
-    copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
-}
-
-print_output_directory() {
-    case ${PKGTYPE} in
-    "deb")
-        echo "${PACKAGE_DEB}"
-        ;;
-    "rpm")
-        echo "${PACKAGE_RPM}"
-        ;;
-    *)
-        echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
-        exit 1
-        ;;
-    esac
-    exit
-}
-
-verifyEnvSetup
-
-case "$TARGET" in
-clean) clean ;;
-build) build_omnitrace ;;
-outdir) print_output_directory ;;
-*) die "Invalid target $TARGET" ;;
-esac
-
-echo "Operation complete"

tools/rocm-build/build_opencl_icd_loader.sh

@@ -1,141 +0,0 @@
-#!/bin/bash
-
-source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
-PROJ_NAME=OpenCL-ICD-Loader
-TARGET="build"
-MAKEOPTS="$DASH_JAY"
-BUILD_TYPE="Debug"
-PACKAGE_ROOT="$(getPackageRoot)"
-PACKAGE_DEB="$PACKAGE_ROOT/deb/${PROJ_NAME,,}"
-PACKAGE_RPM="$PACKAGE_ROOT/rpm/${PROJ_NAME,,}"
-CLEAN_OR_OUT=0;
-PKGTYPE="deb"
-MAKETARGET="deb"
-API_NAME="rocm-opencl-icd-loader"
-
-printUsage() {
-    echo
-    echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
-    echo
-    echo "Options:"
-    echo "  -c,  --clean              Clean output and delete all intermediate work"
-    echo "  -p,  --package <type>     Specify packaging format"
-    echo "  -r,  --release            Make a release build instead of a debug build"
-    echo "  -h,  --help               Prints this help"
-    echo "  -o,  --outdir             Print path of output directory containing packages"
-    echo "  -s,  --static             Component/Build does not support static builds just accepting this param & ignore. No effect of the param on this build"
-    echo
-    echo "Possible values for <type>:"
-    echo "  deb -> Debian format (default)"
-    echo "  rpm -> RPM format"
-    echo
-    return 0
-}
-
-RET_CONFLICT=1
-check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
-if [ $RET_CONFLICT -ge 30 ]; then
-   print_vars $TARGET $BUILD_TYPE $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
-   exit $RET_CONFLICT
-fi
-
-clean_opencl_icd_loader() {
-    echo "Cleaning $PROJ_NAME"
-    rm -rf "$PACKAGE_DEB"
-    rm -rf "$PACKAGE_RPM"
-    rm -rf "$PACKAGE_ROOT/${PROJ_NAME,,}"
-}
-
-copy_pkg_files_to_rocm() {
-    local comp_folder=$1
-    local comp_pkg_name=$2
-
-    cd "${OUT_DIR}/${PKGTYPE}/${comp_folder}"|| exit 2
-    if [ "${PKGTYPE}" = 'deb' ]; then
-        dpkg-deb -x ${comp_pkg_name}_*.deb pkg/
-    else
-        mkdir pkg && pushd pkg/ || exit 2
-        if [[ "${comp_pkg_name}" != *-dev* ]]; then
-            rpm2cpio ../${comp_pkg_name}-*.rpm | cpio -idmv
-        else
-            rpm2cpio ../${comp_pkg_name}el-*.rpm | cpio -idmv
-        fi
-        popd || exit 2
-    fi
-    ls ./pkg -alt
-    cp -r ./pkg/*/rocm*/* "${ROCM_PATH}" || exit 2
-    rm -rf pkg/
-}
-
-build_opencl_icd_loader() {
-    echo "Downloading $PROJ_NAME" package
-    if [ "$DISTRO_NAME" = ubuntu ]; then
-        mkdir -p "$PACKAGE_DEB"
-        local rocm_ver=${ROCM_VERSION}
-        if [ ${ROCM_VERSION##*.} = 0 ]; then
-            rocm_ver=${ROCM_VERSION%.*}
-        fi
-        local url="https://repo.radeon.com/rocm/apt/${rocm_ver}/pool/main/r/${API_NAME}/"
-        local package
-        package=$(curl -s "$url" | grep -Po 'href="\K[^"]*' | grep "${DISTRO_RELEASE}" | head -n 1)
-
-        if [ -z "$package" ]; then
-            echo "No package found for Ubuntu version $DISTRO_RELEASE"
-            exit 1
-        fi
-
-        wget -t3 -P "$PACKAGE_DEB" "${url}${package}"
-        copy_pkg_files_to_rocm ${PROJ_NAME,,} ${API_NAME}
-    else
-        echo "$DISTRO_ID is not supported..."
-        exit 2
-    fi
-
-    echo "Installing $PROJ_NAME" package
-}
-
-print_output_directory() {
-    case ${PKGTYPE} in
-        ("deb")
-            echo ${PACKAGE_DEB};;
-        ("rpm")
-            echo ${PACKAGE_RPM};;
-        (*)
-            echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
-    esac
-    exit
-}
-
-VALID_STR=`getopt -o hcraswlo:p: --long help,clean,release,outdir:,package: -- "$@"`
-eval set -- "$VALID_STR"
-while true ;
-do
-    case "$1" in
-        (-c  | --clean )
-            TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
-        (-r  | --release )
-            BUILD_TYPE="RelWithDebInfo" ; shift ;;
-        (-h  | --help )
-            printUsage ; exit 0 ;;
-        (-a  | --address_sanitizer)
-            ack_and_ignore_asan ; shift ;;
-        (-o  | --outdir)
-            TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
-        (-p | --package)
-            MAKETARGET="$2" ; shift 2;;
-	(-s | --static)
-            echo "-s parameter accepted but ignored" ; shift ;;
-        --)     shift; break;;
-        (*)
-            echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
-    esac
-done
-
-case $TARGET in
-    (clean) clean_opencl_icd_loader ;;
-    (build) build_opencl_icd_loader ;;
-    (outdir) print_output_directory ;;
-    (*) die "Invalid target $TARGET" ;;
-esac
-
-echo "Operation complete"

tools/rocm-build/build_rocm-cmake.sh

@@ -32,7 +32,6 @@ ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
 ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
 ROCM_CMAKE_PACKAGE_DEB="$(getPackageRoot)/deb/rocm-cmake"
 ROCM_CMAKE_PACKAGE_RPM="$(getPackageRoot)/rpm/rocm-cmake"
-ROCM_WHEEL_DIR="${ROCM_CMAKE_BUILD_DIR}/_wheel"
 ROCM_CMAKE_BUILD_TYPE="debug"
 BUILD_TYPE="Debug"
 SHARED_LIBS="ON"
@@ -56,8 +55,6 @@ do
                 ack_and_ignore_asan ; shift ;;
         (-s | --static)
                 SHARED_LIBS="OFF" ; shift ;;
-        (-w | --wheel)
-            WHEEL_PACKAGE=true ; shift ;;
         (-o | --outdir)
                 TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
         (-p | --package)
@@ -78,7 +75,6 @@ fi
 
 
 clean_rocm_cmake() {
-    rm -rf "$ROCM_WHEEL_DIR"
     rm -rf $ROCM_CMAKE_BUILD_DIR
     rm -rf $ROCM_CMAKE_PACKAGE_DEB
     rm -rf $ROCM_CMAKE_PACKAGE_RPM
@@ -106,19 +102,6 @@ build_rocm_cmake() {
     copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$ROCM_CMAKE_PACKAGE_RPM" $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm
 }
 
-create_wheel_package() {
-    echo "Creating rocm-cmake wheel package"
-    # Copy the setup.py generator to build folder
-    mkdir -p $ROCM_WHEEL_DIR
-    cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
-    cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
-    cd $ROCM_WHEEL_DIR
-    # Currently only supports python3.6
-    ./repackage_wheel.sh $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm python3.6
-    # Copy the wheel created to RPM folder which will be uploaded to artifactory
-    copy_if WHL "WHL" "$ROCM_CMAKE_PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
-}
-
 print_output_directory() {
     case ${PKGTYPE} in
         ("deb")
@@ -138,9 +121,4 @@ case $TARGET in
     (*) die "Invalid target $TARGET" ;;
 esac
 
-if [[ $WHEEL_PACKAGE == true ]]; then
-    echo "Wheel Package build started !!!!"
-    create_wheel_package
-fi
-
 echo "Operation complete"

tools/rocm-build/docker/ubuntu20/packages

@@ -7,7 +7,6 @@ bison
 bridge-utils
 build-essential
 bzip2
-ccache
 check
 chrpath
 cifs-utils
@@ -121,11 +120,9 @@ python3-yaml
 python3.8-dev
 re2c
 redis-tools
-# Eventually we should be able to remove rpm for debian builds.
 rpm
 rsync
 ssh
-# This makes life more pleasent inside the container
 strace
 sudo
 systemtap-sdt-dev

tools/rocm-build/docker/ubuntu22/install-prerequisities.sh

@@ -1,285 +0,0 @@
-#! /usr/bin/bash
-
-set -x
-
-apt-get -y update 
-DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(sed 's/#.*//' /tmp/packages)
-apt-get clean 
-rm -rf /var/cache/apt/ /var/lib/apt/lists/* /etc/apt/apt.conf.d/01proxy
-
-#Install  2.17.1 version of git as we are seeing issues with 2.25 , where it was not allowing to add git submodules if the user is different for parent git directory
-curl -o git.tar.gz https://cdn.kernel.org/pub/software/scm/git/git-2.17.1.tar.gz 
-tar -zxf git.tar.gz 
-cd git-* 
-make prefix=/usr/local all    
-make prefix=/usr/local install
-git --version
-
-#install argparse and CppHeaderParser python modules for roctracer and rocprofiler
-#install rocm-docs-core for the docs-as-code project. Only needed on one OS
-# CppHeader needs setuptools. setuptools needs wheel.
-# Looks like I need them as seperate commands
-# Sigh, install both python2 and python 3 version
-pip3 install --no-cache-dir setuptools wheel tox
-pip3 install --no-cache-dir CppHeaderParser argparse requests lxml barectf recommonmark jinja2==3.0.0 websockets matplotlib numpy scipy minimal msgpack pytest sphinx joblib PyYAML rocm-docs-core cmake==3.25.2 pandas myst-parser
-
-# Allow sudo for everyone user
-echo 'ALL ALL=(ALL) NOPASSWD:ALL' > /etc/sudoers.d/everyone
-
-# Install OCaml packages to build LLVM's OCaml bindings to be used in lightning compiler test pipeline
-wget -nv https://sourceforge.net/projects/opam.mirror/files/2.1.4/opam-2.1.4-x86_64-linux -O /usr/local/bin/opam 
-chmod +x /usr/local/bin/opam
-opam init --yes --disable-sandboxing
-opam install ctypes --yes
-
-# Install and modify git-repo (#!/usr/bin/env python -> #!/usr/bin/env python3)
-curl https://storage.googleapis.com/git-repo-downloads/repo > /usr/bin/repo
-chmod a+x /usr/bin/repo
-
-# Build ccache from the source
-cd /tmp 
-git clone https://github.com/ccache/ccache -b v4.7.5 
-cd ccache 
-mkdir build 
-cd build 
-cmake -DCMAKE_BUILD_TYPE=Release .. 
-make 
-make install 
-cd /tmp 
-rm -rf ccache
-
-# Install sharp from MLNX_OFED_LINUX as dependency for rccl-rdma-sharp-plugins
-cd /var/tmp
-mkdir mlnx 
-wget -O mlnx/tar.tgz https://content.mellanox.com/ofed/MLNX_OFED-24.01-0.3.3.1/MLNX_OFED_LINUX-24.01-0.3.3.1-ubuntu22.04-x86_64.tgz 
-tar -xz -C mlnx -f mlnx/tar.tgz 
-apt-key add mlnx/*/RPM-GPG-KEY-Mellanox
-echo "deb [arch=amd64] file:$(echo $PWD/mlnx/*/DEBS) ./" > /etc/apt/sources.list.d/sharp.list
-apt update
-apt install -y sharp 
-apt clean
-rm -rf /var/cache/apt/ /var/lib/apt/lists/* mlnx /etc/apt/sources.list.d/sharp.list
-
-apt update
-apt -y install libunwind-dev
-apt -y install libgoogle-glog-dev
-
-# Install python3.8 from source
-curl -LO https://www.python.org/ftp/python/3.8.13/Python-3.8.13.tar.xz
-tar -xvf Python-3.8.13.tar.xz
-pwd
-ls /var/tmp/
-ls Python-3.8.13
-mv Python-3.8.13 /opt/
-apt install build-essential zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libsqlite3-dev libreadline-dev libffi-dev curl libbz2-dev pkg-config make -y 
-cd /opt/Python-3.8.13/ 
-./configure --enable-optimizations --enable-shared
-make 
-make -j 6 
-make altinstall 
-ldconfig /opt/Python3.8.13
-python3.8 --version
-
-# roctracer and rocprofiler needs this python3.8
-python3.8 -m pip install setuptools wheel
-python3.8 -m pip install CppHeaderParser argparse requests lxml PyYAML joblib
-
-#Install older version of hwloc-devel package for rocrtst
-curl -lO https://download.open-mpi.org/release/hwloc/v1.11/hwloc-1.11.13.tar.bz2
-tar -xvf hwloc-1.11.13.tar.bz2
-cd hwloc-1.11.13
-./configure
-make
-make install
-cp /usr/local/lib/libhwloc.so.5 /usr/lib
-hwloc-info --version
-
-# Install gtest
-mkdir -p /tmp/gtest
-cd /tmp/gtest
-wget https://github.com/google/googletest/archive/refs/tags/v1.14.0.zip -O googletest.zip
-unzip googletest.zip
-cd googletest-1.14.0/ 
-mkdir build
-cd build
-cmake .. 
-make -j$(nproc) 
-make install
-rm -rf /tmp/gtest
-
-## Install gRPC from source
-## RDC Pre-requisites
-GRPC_ARCHIVE=grpc-1.61.0.tar.gz
-mkdir /tmp/grpc
-mkdir /usr/grpc 
-cd /tmp 
-git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
-cd grpc
-mkdir -p build 
-cd build
-cmake  -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' .. 
-make -j $(nproc) install 
-rm -rf /tmp/grpc
-
-## rocBLAS Pre-requisites
-## Download prebuilt AMD multithreaded blis (2.0)
-## Reference : https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/install.sh#L403
-mkdir -p /tmp/blis 
-cd /tmp/blis
-wget -O - https://github.com/amd/blis/releases/download/2.0/aocl-blis-mt-ubuntu-2.0.tar.gz | tar xfz - 
-mv amd-blis-mt /usr/blis 
-cd / 
-rm -rf /tmp/blis
-
-## rocBLAS Pre-requisites(SWDEV-404612)
-## Download aocl-linux-gcc-4.2.0_1_amd64.deb
-mkdir -p /tmp/aocl 
-cd /tmp/aocl 
-wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb 
-apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb 
-rm -rf /tmp/aocl
-
-## hipBLAS Pre-requisites
-## lapack(3.9.1v)
-## Reference https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/install.sh#L174
-lapack_version=3.9.1
-lapack_srcdir=lapack-$lapack_version
-lapack_blddir=lapack-$lapack_version-bld
-mkdir -p /tmp/lapack
-cd /tmp/lapack
-rm -rf "$lapack_srcdir" "$lapack_blddir" 
-wget -O - https://github.com/Reference-LAPACK/lapack/archive/refs/tags/v3.9.1.tar.gz | tar xzf - 
-cmake -H$lapack_srcdir -B$lapack_blddir -DCMAKE_BUILD_TYPE=Release -DCMAKE_Fortran_FLAGS=-fno-optimize-sibling-calls -DBUILD_TESTING=OFF -DCBLAS=ON -DLAPACKE=OFF
-make -j$(nproc) -C "$lapack_blddir"
-make -C "$lapack_blddir" install
-cd $lapack_blddir
-cp -r ./include/* /usr/local/include/ 
-cp -r ./lib/* /usr/local/lib 
-cd / 
-rm -rf /tmp/lapack
-
-## rocSOLVER Pre-requisites
-## FMT(7.1.3v)
-## Reference https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/install.sh#L152
-fmt_version=7.1.3
-fmt_srcdir=fmt-$fmt_version
-fmt_blddir=fmt-$fmt_version-bld
-mkdir -p /tmp/fmt
-cd /tmp/fmt
-rm -rf "$fmt_srcdir" "$fmt_blddir"
-wget -O - https://github.com/fmtlib/fmt/archive/refs/tags/7.1.3.tar.gz | tar xzf -
-cmake -H$fmt_srcdir -B$fmt_blddir -DCMAKE_BUILD_TYPE=Release -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_CXX_STANDARD=17 -DCMAKE_CXX_EXTENSIONS=OFF -DCMAKE_CXX_STANDARD_REQUIRED=ON -DFMT_DOC=OFF -DFMT_TEST=OFF
-make -j$(nproc) -C "$fmt_blddir"
-make -C "$fmt_blddir" install
-
-# Build and install libjpeg-turbo
-mkdir -p /tmp/libjpeg-turbo 
-cd /tmp/libjpeg-turbo 
-wget -nv https://github.com/rrawther/libjpeg-turbo/archive/refs/heads/2.0.6.2.zip -O libjpeg-turbo-2.0.6.2.zip
-unzip libjpeg-turbo-2.0.6.2.zip 
-cd libjpeg-turbo-2.0.6.2
-mkdir build
-cd build
-cmake -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_BUILD_TYPE=RELEASE -DENABLE_STATIC=FALSE -DCMAKE_INSTALL_DEFAULT_LIBDIR=lib .. 
-make -j$(nproc) install 
-rm -rf /tmp/libjpeg-turbo
-
-# Get released ninja from source
-mkdir -p /tmp/ninja 
-cd /tmp/ninja 
-wget -nv https://codeload.github.com/Kitware/ninja/zip/refs/tags/v1.11.1.g95dee.kitware.jobserver-1 -O ninja.zip
-unzip ninja.zip
-cd ninja-1.11.1.g95dee.kitware.jobserver-1
-./configure.py --bootstrap 
-cp ninja /usr/local/bin/ 
-rm -rf /tmp/ninja
-
-# Install  FFmpeg and dependencies
-# Build NASM
-mkdir -p /tmp/nasm-2.15.05 
-cd /tmp
-wget -qO- "https://distfiles.macports.org/nasm/nasm-2.15.05.tar.bz2" | tar -xvj 
-cd nasm-2.15.05
-./autogen.sh
-./configure --prefix="/usr/local"
-make -j$(nproc) install
-rm -rf /tmp/nasm-2.15.05
-
-# Build YASM
-mkdir -p /tmp/yasm-1.3.0 
-cd /tmp
-wget -qO- "http://www.tortall.net/projects/yasm/releases/yasm-1.3.0.tar.gz" | tar -xvz 
-cd yasm-1.3.0
-./configure --prefix="/usr/local"
-make -j$(nproc) install
-rm -rf /tmp/yasm-1.3.0
-
-# Build x264
-mkdir -p /tmp/x264-snapshot-20191217-2245-stable
-cd /tmp
-wget -qO-  "https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-20191217-2245-stable.tar.bz2" | tar -xvj
-cd /tmp/x264-snapshot-20191217-2245-stable
-PKG_CONFIG_PATH="/usr/local/lib/pkgconfig" ./configure --prefix="/usr/local" --enable-shared
-make -j$(nproc) install
-rm -rf /tmp/x264-snapshot-20191217-2245-stable
-
-# Build x265
-mkdir -p /tmp/x265_2.7
-cd /tmp
-wget -qO- "https://get.videolan.org/x265/x265_2.7.tar.gz" | tar -xvz
-cd  /tmp/x265_2.7/build/linux
-cmake -G "Unix Makefiles" -DCMAKE_INSTALL_PREFIX="/usr/local" -DENABLE_SHARED:bool=on ../../source
-make -j$(nproc) install
-rm -rf /tmp/x265_2.7
-
-# Build fdk-aac
-mkdir -p /tmp/fdk-aac-2.0.2
-cd /tmp
-wget -qO- "https://sourceforge.net/projects/opencore-amr/files/fdk-aac/fdk-aac-2.0.2.tar.gz" | tar -xvz
-cd /tmp/fdk-aac-2.0.2
-autoreconf -fiv
-./configure --prefix="/usr/local" --enable-shared --disable-static
-make -j$(nproc) install
-rm -rf /tmp/fdk-aac-2.0.2
-
-# Build FFmpeg
-cd /tmp
-git clone -b release/4.4 https://git.ffmpeg.org/ffmpeg.git ffmpeg
-cd ffmpeg
-PKG_CONFIG_PATH="/usr/local/lib/pkgconfig"
-./configure  --prefix="/usr/local" --extra-cflags="-I/usr/local/include"   --extra-ldflags="-L/usr/local/lib"  --extra-libs=-lpthread  --extra-libs=-lm  --enable-shared   --disable-static   --enable-libx264  --enable-libx265  --enable-libfdk-aac  --enable-gpl --enable-nonfree
-make -j$(nproc) install
-rm -rf /tmp/ffmpeg
-
-cp /tmp/local-pin-600 /etc/apt/preferences.d
-
-command -v lbzip2 
-ln -sf $(command -v lbzip2) /usr/local/bin/compressor || ln -sf $(command -v bzip2) /usr/local/bin/compressor
-
-# Install Google Benchmark
-mkdir -p /tmp/Gbenchmark 
-cd /tmp/Gbenchmark 
-wget -qO- https://github.com/google/benchmark/archive/refs/tags/v1.6.1.tar.gz | tar xz 
-cmake -Sbenchmark-1.6.1 -Bbuild -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=OFF -DBENCHMARK_ENABLE_TESTING=OFF -DCMAKE_CXX_STANDARD=14 
-make -j -C build 
-cd /tmp/Gbenchmark/build
-make install
-
-# Build boost-1.85.0 from source for RPP
-# Installing in a non-standard location since the test packages of hipFFT and rocFFT pick up the version of
-# the installed Boost library and declare a package dependency on that specific version of Boost.
-# For example, if this was installed in the standard location it would declare a dependency on libboost-dev(el)1.85.0
-# which is not available as a package in any distro.
-# Once this is fixed, we can remove the Boost package from the requirements list and install this
-# in the standard location
-mkdir -p /tmp/boost-1.85.0 
-cd /tmp/boost-1.85.0 
-wget -nv https://sourceforge.net/projects/boost/files/boost/1.85.0/boost_1_85_0.tar.bz2 -O ./boost_1_85_0.tar.bz2 
-tar -xf boost_1_85_0.tar.bz2 --use-compress-program="/usr/local/bin/compressor" 
-cd boost_1_85_0 
-./bootstrap.sh --prefix=${RPP_DEPS_LOCATION} --with-python=python3 
-./b2 stage -j$(nproc) threading=multi link=shared cxxflags="-std=c++11" 
-./b2 install threading=multi link=shared --with-system --with-filesystem 
-./b2 stage -j$(nproc) threading=multi link=static cxxflags="-std=c++11 -fpic" cflags="-fpic"
-./b2 install threading=multi link=static --with-system --with-filesystem 
-rm -rf /tmp/boost-1.85.0

tools/rocm-build/docker/ubuntu22/packages

@@ -7,7 +7,6 @@ bison
 bridge-utils
 build-essential
 bzip2
-ccache
 check
 chrpath
 cifs-utils