[Ex CI] Added rocsparse as a dependency for hipsparselt (#5867 )

* [Ex CI] Added rocsparse as a dependency for hipsparselt * Fix component typo
Use intersphinx links for deep learning (#5859 )
2026-01-20 12:08:09 -05:00 · 2026-01-19 16:45:49 -05:00 · 2026-01-16 13:17:47 -08:00 · 2026-01-16 12:55:55 -05:00 · 2026-01-16 10:25:40 -05:00 · 2026-01-16 06:54:25 -07:00
7 changed files with 170 additions and 40 deletions
--- a/.azuredevops/components/hipSPARSE.yml
+++ b/.azuredevops/components/hipSPARSE.yml
@@ -32,7 +32,6 @@ parameters:
 - name: aptPackages
  type: object
  default:
-    - cmake
    - gfortran
    - git
    - libboost-program-options-dev
@@ -42,6 +41,7 @@ parameters:
 - name: rocmDependencies
  type: object
  default:
+    - aomp
    - clr
    - llvm-project
    - rocminfo
@@ -51,6 +51,7 @@ parameters:
 - name: rocmTestDependencies
  type: object
  default:
+    - aomp
    - clr
    - llvm-project
    - hipBLAS-common
@@ -103,6 +104,7 @@ jobs:
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
@@ -128,6 +130,7 @@ jobs:
          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
+          -DCMAKE_Fortran_COMPILER=gfortran
          -DCMAKE_BUILD_TYPE=Release
          -DBUILD_CLIENTS_TESTS=ON
          -DBUILD_CLIENTS_SAMPLES=OFF
--- a/.azuredevops/components/hipSPARSELt.yml
+++ b/.azuredevops/components/hipSPARSELt.yml
@@ -60,6 +60,7 @@ parameters:
    - rocprofiler-register
    - ROCR-Runtime
    - roctracer
+    - rocSPARSE
 - name: rocmTestDependencies
  type: object
  default:
@@ -74,6 +75,7 @@ parameters:
    - rocprofiler-register
    - ROCR-Runtime
    - roctracer
+    - rocSPARSE

 - name: jobMatrix
  type: object
--- a/docs/how-to/deep-learning-rocm.rst
+++ b/docs/how-to/deep-learning-rocm.rst
@@ -24,7 +24,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
      - GitHub

    * - :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`
-      - :doc:`Pytorch install <rocm-install-on-linux:install/3rd-party/pytorch-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/pytorch-install>`
      - 
        - Docker image
        - Wheels package
@@ -35,7 +35,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/pytorch"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`
-      - :doc:`TensorFlow install <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
      - 
        - Docker image
        - Wheels package
@@ -45,7 +45,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/tensorflow-upstream"><i class="fab fa-github fa-lg"></i></a> 

    * - :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`
-      - :doc:`JAX install <rocm-install-on-linux:install/3rd-party/jax-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/jax-install>`
      - 
        - Docker image
      - .. raw:: html
@@ -53,7 +53,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/jax"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>`
-      - :doc:`verl install <rocm-install-on-linux:install/3rd-party/verl-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/verl-install>`
      - 
        - Docker image
      - .. raw:: html
@@ -61,7 +61,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/verl"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
-      - :doc:`Stanford Megatron-LM install <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
      - 
        - Docker image
      - .. raw:: html
@@ -69,7 +69,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/Stanford-Megatron-LM"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`
-      - :doc:`DGL install <rocm-install-on-linux:install/3rd-party/dgl-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/dgl-install>`
      - 
        - Docker image
      - .. raw:: html
@@ -77,24 +77,15 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/dgl"><i class="fab fa-github fa-lg"></i></a> 

    * - :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`
-      - :doc:`Megablocks install <rocm-install-on-linux:install/3rd-party/megablocks-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/megablocks-install>`
      - 
        - Docker image
      - .. raw:: html

          <a href="https://github.com/ROCm/megablocks"><i class="fab fa-github fa-lg"></i></a>

-    * - :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>`
-      - `Taichi install <https://rocm.docs.amd.com/projects/taichi/en/latest/install/taichi-install.html>`__
-      - 
-        - Docker image
-        - Wheels package
-      - .. raw:: html
-
-          <a href="https://github.com/ROCm/taichi"><i class="fab fa-github fa-lg"></i></a>
-
    * - :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>`
-      - :doc:`Ray install <rocm-install-on-linux:install/3rd-party/ray-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/ray-install>`
      - 
        - Docker image
        - Wheels package
@@ -104,7 +95,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/ray"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>`
-      - :doc:`llama.cpp install <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
      - 
        - Docker image
        - ROCm Base Docker image
@@ -113,7 +104,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>`
-      - :doc:`FlashInfer install <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
      - 
        - Docker image
        - ROCm Base Docker image
--- a/docs/reference/gpu-arch-specs.rst
+++ b/docs/reference/gpu-arch-specs.rst
@@ -5,7 +5,7 @@
 GPU hardware specifications
 ===========================================

-The following tables provide an overview of the hardware specifications for AMD Instinct™ GPUs, and AMD Radeon™ PRO and Radeon™ GPUs.
+The following tables provide an overview of the hardware specifications for AMD Instinct™ GPUs, AMD Radeon™ PRO and Radeon™ GPUs, and AMD Ryzen™ APUs.

 For more information about ROCm hardware compatibility, see the ROCm `Compatibility matrix <https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html>`_.

@@ -18,7 +18,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
        :name: instinct-arch-spec-table

        *
-          - Model
+          - Name
          - Architecture
          - LLVM target name
          - VRAM (GiB)
@@ -297,7 +297,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
        :name: radeon-pro-arch-spec-table

        *
-          - Model
+          - Name
          - Architecture
          - LLVM target name

@@ -539,7 +539,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
        :name: radeon-arch-spec-table

        *
-          - Model
+          - Name
          - Architecture
          - LLVM target name
          - VRAM (GiB)
@@ -953,6 +953,127 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 9
          - 0

+  .. tab-item:: AMD Ryzen APUs
+
+    .. list-table::
+        :header-rows: 1
+        :name: ryzen-arch-spec-table
+
+        *
+          - Name
+          - Graphics model
+          - Architecture
+          - LLVM target name
+          - VRAM (GiB)
+          - Compute Units
+          - Wavefront Size
+          - LDS (KiB)
+          - Infinity Cache (MiB)
+          - L2 Cache (MiB)
+          - Graphics L1 Cache (KiB)
+          - L0 Vector Cache (KiB)
+          - L0 Scalar Cache (KiB)
+          - L0 Instruction Cache (KiB)
+          - VGPR File (KiB)
+          - SGPR File (KiB)
+          - GFXIP Major version
+          - GFXIP Minor version
+        *
+          - AMD Ryzen 7 7840U
+          - Radeon 780M
+          - RDNA3
+          - gfx1103
+          - Dynamic + carveout
+          - 12
+          - 32 or 64
+          - 128
+          - N/A
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 0
+        *
+          - AMD Ryzen 9 270
+          - Radeon 780M
+          - RDNA3
+          - gfx1103
+          - Dynamic + carveout
+          - 12
+          - 32 or 64
+          - 128
+          - N/A
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 0
+        *
+          - AMD Ryzen AI 9 HX 375
+          - Radeon 890M
+          - RDNA3.5
+          - gfx1150
+          - Dynamic + carveout
+          - 16
+          - 32 or 64
+          - 128
+          - N/A
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 5
+        *
+          - AMD Ryzen AI Max+ PRO 395
+          - Radeon 8060S
+          - RDNA3.5
+          - gfx1151
+          - Dynamic + carveout
+          - 40
+          - 32 or 64
+          - 128
+          - 32
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 768
+          - 32
+          - 11
+          - 5
+        *
+          - AMD Ryzen Al 7 350
+          - Radeon 860M
+          - RDNA3.5
+          - gfx1152
+          - Dynamic + carveout
+          - 8
+          - 32 or 64
+          - 128
+          - N/A
+          - 1
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 5
+
 Glossary
 ========

--- a/docs/sphinx/_toc.yml.in
+++ b/docs/sphinx/_toc.yml.in
@@ -29,27 +29,25 @@ subtrees:
    title: Deep learning frameworks
    subtrees:
    - entries:
-      - file: compatibility/ml-compatibility/pytorch-compatibility
+      - file: compatibility/ml-compatibility/pytorch-compatibility.rst
        title: PyTorch compatibility
-      - file: compatibility/ml-compatibility/tensorflow-compatibility
+      - file: compatibility/ml-compatibility/tensorflow-compatibility.rst
        title: TensorFlow compatibility
-      - file: compatibility/ml-compatibility/jax-compatibility
+      - file: compatibility/ml-compatibility/jax-compatibility.rst
        title: JAX compatibility
-      - file: compatibility/ml-compatibility/verl-compatibility
+      - file: compatibility/ml-compatibility/verl-compatibility.rst
        title: verl compatibility
-      - file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility
+      - file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst
        title: Stanford Megatron-LM compatibility
-      - file: compatibility/ml-compatibility/dgl-compatibility
+      - file: compatibility/ml-compatibility/dgl-compatibility.rst
        title: DGL compatibility
-      - file: compatibility/ml-compatibility/megablocks-compatibility
+      - file: compatibility/ml-compatibility/megablocks-compatibility.rst
        title: Megablocks compatibility
-      - file: compatibility/ml-compatibility/taichi-compatibility
-        title: Taichi compatibility
-      - file: compatibility/ml-compatibility/ray-compatibility
+      - file: compatibility/ml-compatibility/ray-compatibility.rst
        title: Ray compatibility
-      - file: compatibility/ml-compatibility/llama-cpp-compatibility
+      - file: compatibility/ml-compatibility/llama-cpp-compatibility.rst
        title: llama.cpp compatibility
-      - file: compatibility/ml-compatibility/flashinfer-compatibility
+      - file: compatibility/ml-compatibility/flashinfer-compatibility.rst
        title: FlashInfer compatibility
  - file: how-to/build-rocm.rst
    title: Build ROCm from source
@@ -77,8 +75,14 @@ subtrees:
        - entries:
          - file: how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
            title: Train a model with Primus and Megatron-LM
+            entries:
+            - file: how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
+              title: Train a model with Megatron-LM
          - file: how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
            title: Train a model with Primus and PyTorch
+            entries:
+            - file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
+              title: Train a model with PyTorch
          - file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
            title: Train a model with JAX MaxText
          - file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
@@ -117,6 +121,8 @@ subtrees:
            title: SGLang inference performance testing
          - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
            title: SGLang distributed inference with Mooncake
+          - file: how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
+            title: xDiT diffusion inference
          - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
            title: Deploy your model

@@ -134,6 +140,8 @@ subtrees:
            title: Profile and debug
          - file: how-to/rocm-for-ai/inference-optimization/workload.rst
            title: Workload optimization
+          - file: how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst
+            title: vLLM V1 performance optimization

      - url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
        title: AI tutorials
@@ -180,7 +188,7 @@ subtrees:
          - file: conceptual/gpu-arch/mi300-mi200-performance-counters.rst
            title: MI300 and MI200 performance counters
          - file: conceptual/gpu-arch/mi350-performance-counters.rst
-            title: MI350 series performance counters
+            title: MI350 Series performance counters
      - file: conceptual/gpu-arch/mi250.md
        title: MI250 microarchitecture
        subtrees:
@@ -214,6 +222,8 @@ subtrees:
    title: ROCm tools, compilers, and runtimes
  - file: reference/gpu-arch-specs.rst
  - file: reference/gpu-atomics-operation.rst
+  - file: reference/env-variables.rst
+    title: Environment variables
  - file: reference/precision-support.rst
    title: Data types and precision support
  - file: reference/graph-safe-support.rst
--- a/docs/sphinx/requirements.in
+++ b/docs/sphinx/requirements.in
@@ -1,4 +1,4 @@
-rocm-docs-core==1.31.2
+rocm-docs-core==1.31.3
 sphinx-reredirects
 sphinx-sitemap
 sphinxcontrib.datatemplates==0.11.0
--- a/docs/sphinx/requirements.txt
+++ b/docs/sphinx/requirements.txt
@@ -188,7 +188,7 @@ requests==2.32.5
    # via
    #   pygithub
    #   sphinx
-rocm-docs-core==1.31.2
+rocm-docs-core==1.31.3
    # via -r requirements.in
 rpds-py==0.30.0
    # via
@@ -214,6 +214,7 @@ sphinx==8.1.3
    #   sphinx-design
    #   sphinx-external-toc
    #   sphinx-last-updated-by-git
+    #   sphinx-multitoc-numbering
    #   sphinx-notfound-page
    #   sphinx-reredirects
    #   sphinxcontrib-datatemplates
@@ -224,10 +225,12 @@ sphinx-copybutton==0.5.2
    # via rocm-docs-core
 sphinx-design==0.6.1
    # via rocm-docs-core
-sphinx-external-toc==1.0.1
+sphinx-external-toc==1.1.0
    # via rocm-docs-core
 sphinx-last-updated-by-git==0.3.8
    # via sphinx-sitemap
+sphinx-multitoc-numbering==0.1.3
+    # via sphinx-external-toc
 sphinx-notfound-page==1.1.0
    # via rocm-docs-core
 sphinx-reredirects==0.1.6
Author	SHA1	Message	Date
amd-hsivasun	8aa43d132f	[Ex CI] Added rocsparse as a dependency for hipsparselt (#5867 ) * [Ex CI] Added rocsparse as a dependency for hipsparselt * Fix component typo	2026-01-19 16:45:49 -05:00
randyh62	45bd726f55	Use intersphinx links for deep learning (#5859 ) * Use intersphinx links for deep learning * Update deep-learning-rocm.rst remove Taichi * Update deep-learning-rocm.rst Change Install link to "link" * Apply suggestion from @randyh62 OK	2026-01-16 13:17:47 -08:00
Jeffrey Novotny	33fbde69db	Add missing APU entries to GPU hardware specifications (#646 ) (#5862 ) * Add missing APU entries to GPU hardware specifications * Move Ryzen APUs to new tab * Add new column to Ryzen table and rename column elsewhere --------- (cherry picked from commit 7ab402a3b3e580ca27321635596ca14eca8c1277) Co-authored-by: alexxu-amd <159800977+alexxu-amd@users.noreply.github.com>	2026-01-16 12:55:55 -05:00
Alex Xu	2851f89992	update rocm-docs-core version to 1.31.3	2026-01-16 10:25:40 -05:00
David Dixon	d31ca06bea	Fix Azure failures introduced by hipsparse build system refactor (#5857 )	2026-01-16 06:54:25 -07:00