Precision support page update

2026-01-11 07:38:17 -05:00 · 2025-02-04 15:03:31 +01:00
17 changed files with 133 additions and 314 deletions
--- a/.azuredevops/components/MIOpen.yml
+++ b/.azuredevops/components/MIOpen.yml
@@ -101,7 +101,7 @@ jobs:
        -DMIOPEN_BACKEND=HIP
        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/miopen-deps
-        -DGPU_TARGETS=$(JOB_GPU_TARGET)
+        -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
        -DMIOPEN_ENABLE_AI_KERNEL_TUNING=OFF
        -DMIOPEN_ENABLE_AI_IMMED_MODE_FALLBACK=OFF
        -DCMAKE_BUILD_TYPE=Release
@@ -129,8 +129,6 @@ jobs:
  variables:
  - group: common
  - template: /.azuredevops/variables-global.yml
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
  pool: $(JOB_TEST_POOL)
  workspace:
    clean: all
--- a/.azuredevops/components/ROCR-Runtime.yml
+++ b/.azuredevops/components/ROCR-Runtime.yml
@@ -123,13 +123,16 @@ jobs:
      targetType: 'inline'
      workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
      script: |
+        sudo rm -rf $(Agent.BuildDirectory)/external/llvm-project
+        mkdir -p $(Agent.BuildDirectory)/external/llvm-project/clang/lib
+        sudo ln -s $(Agent.BuildDirectory)/rocm/llvm/lib/clang/20/include $(Agent.BuildDirectory)/external/llvm-project/clang/lib/Headers
        mkdir build && cd build
        cmake .. \
          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
          -DTARGET_DEVICES=$(JOB_GPU_TARGET) \
          -DROCM_DIR=$(Agent.BuildDirectory)/rocm \
          -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
-          -DOPENCL_INC_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang/21/include
+          -DOPENCL_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin
        make
        make rocrtst_kernels
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
--- a/.azuredevops/components/hipBLASLt.yml
+++ b/.azuredevops/components/hipBLASLt.yml
@@ -59,10 +59,14 @@ jobs:
    value: $(Build.BinariesDirectory)/rocm
  - name: TENSILE_ROCM_ASSEMBLER_PATH
    value: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
+  - name: CMAKE_CXX_COMPILER
+    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
  - name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
    value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
+  - name: TENSILE_ROCM_PATH
+    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
+  - name: PATH
+    value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
  - name: DAY_STRING
    value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
  pool: ${{ variables.ULTRA_BUILD_POOL }}
@@ -150,8 +154,9 @@ jobs:
      extraEnvVars:
        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
        - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/amdclang
+        - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/bin/hipcc
        - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-        - ROCM_PATH:::/home/user/workspace/rocm
+        - TENSILE_ROCM_PATH:::/home/user/workspace/rocm/bin/hipcc
      extraCopyDirectories:
        - deps

--- a/.azuredevops/components/rccl.yml
+++ b/.azuredevops/components/rccl.yml
@@ -51,7 +51,6 @@ parameters:

 jobs:
 - job: rccl
-  timeoutInMinutes: 90
  variables:
  - group: common
  - template: /.azuredevops/variables-global.yml
@@ -79,6 +78,7 @@ jobs:
      checkoutRef: ${{ parameters.checkoutRef }}
      dependencyList: ${{ parameters.rocmDependencies }}
      gpuTarget: $(JOB_GPU_TARGET)
+  - script: chmod +x $(Agent.BuildDirectory)/rocm/bin/hipify-perl
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
    parameters:
      extraBuildFlags: >-
@@ -88,7 +88,7 @@ jobs:
        -DCMAKE_BUILD_TYPE=Release
        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
        -DBUILD_TESTS=ON
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake;$(Agent.BuildDirectory)/rocm/libexec/hipify
+        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
        -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
        -GNinja
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
--- a/.azuredevops/components/rocBLAS.yml
+++ b/.azuredevops/components/rocBLAS.yml
@@ -64,10 +64,10 @@ jobs:
    value: $(Build.BinariesDirectory)/rocm
  - name: TENSILE_ROCM_ASSEMBLER_PATH
    value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
+  - name: CMAKE_CXX_COMPILER
+    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
  - name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
    value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
  pool: ${{ variables.MEDIUM_BUILD_POOL }}
  workspace:
    clean: all
@@ -96,8 +96,8 @@ jobs:
        -DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
        -DCMAKE_BUILD_TYPE=Release
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang++
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
+        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
+        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
        -DGPU_TARGETS=$(JOB_GPU_TARGET)
        -DTensile_CODE_OBJECT_VERSION=default
        -DTensile_LOGIC=asm_full
@@ -125,8 +125,8 @@ jobs:
      extraEnvVars:
        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
        - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
+        - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/bin/hipcc
        - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-        - ROCM_PATH:::/home/user/workspace/rocm

 - job: rocBLAS_testing
  dependsOn: rocBLAS
--- a/.azuredevops/components/rocWMMA.yml
+++ b/.azuredevops/components/rocWMMA.yml
@@ -80,7 +80,6 @@ jobs:
        -DROCWMMA_BUILD_SAMPLES=OFF
        -DGPU_TARGETS=$(JOB_GPU_TARGET)
        -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON
-        -DROCM_PLATFORM_VERSION=$(NEXT_RELEASE_VERSION)
        -GNinja
 # gfx1030 not supported in documentation
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
--- a/.azuredevops/components/rocminfo.yml
+++ b/.azuredevops/components/rocminfo.yml
@@ -56,7 +56,6 @@ jobs:
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
    parameters:
      aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true

 - job: rocminfo_testing
  dependsOn: rocminfo
@@ -103,6 +102,5 @@ jobs:
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
    parameters:
      aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
      environment: test
      gpuTarget: $(JOB_GPU_TARGET)
--- a/.azuredevops/components/rocprofiler-systems.yml
+++ b/.azuredevops/components/rocprofiler-systems.yml
@@ -55,10 +55,9 @@ parameters:
    - rocJPEG
    - rocm-core
    - rocminfo
-    - rocm_smi_lib
+    - ROCR-Runtime
    - rocprofiler-register
    - rocprofiler-sdk
-    - ROCR-Runtime

 jobs:
 - job: rocprofiler_systems
--- a/.github/workflows/issue_retrieval.yml
+++ b/.github/workflows/issue_retrieval.yml
@@ -2,7 +2,7 @@ name: Issue retrieval

 on:
  issues:
-    types: [opened, edited]
+    types: [opened]

 jobs:
  auto-retrieve:
@@ -15,7 +15,7 @@ jobs:
          app_id: ${{ secrets.ACTION_APP_ID }}
          private_key: ${{ secrets.ACTION_PEM }}
      - name: 'Retrieve Issue'
-        uses: harkgill-amd/rocm_issue_management@main
+        uses: abhimeda/rocm_issue_management@main
        with:
          authentication-token: ${{ steps.generate_token.outputs.token }}
          github-organization: 'ROCm'
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -74,7 +74,6 @@ Conda
 ConnectX
 CuPy
 Dashboarding
-DBRX
 DDR
 DF
 DGEMM
@@ -93,7 +92,6 @@ DataFrame
 DataLoader
 DataParallel
 Debian
-DeepSeek
 DeepSpeed
 Dependabot
 Deprecations
@@ -131,8 +129,6 @@ GDS
 GEMM
 GEMMs
 GFortran
-GFXIP
-Gemma
 GiB
 GIM
 GL
--- a/RELEASE.md
+++ b/RELEASE.md
@@ -29,7 +29,8 @@ 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, see the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility/native_linux/native_linux_compatibility.html)
+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)
 documentation to verify compatibility and system requirements.
 ```
 ## Release highlights
--- a/docs/about/license.md
+++ b/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/) | [MIT](https://github.com/ROCm/rocm_bandwidth_test/blob/master/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 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) |
--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/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 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,
+,Debian 12 [#mi300x-past-60]_,Debian 12 [#mi300x-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
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/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 [#single-node]_,Debian 12 [#single-node]_,
+      ,Debian 12 [#mi300x]_,Debian 12 [#mi300x]_,
      ,Azure Linux 3.0 [#mi300x]_,,
      ,.. _architecture-support-compatibility-matrix:,,
      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3
@@ -148,8 +148,7 @@ compatibility and system requirements.

 .. rubric:: Footnotes

-.. [#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. 
+.. [#mi300x] Oracle Linux, Debian, and Azure Linux are supported only on AMD Instinct MI300X.
 .. [#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.
@@ -216,8 +215,7 @@ Expand for full historical view of:

   .. rubric:: Footnotes

-   .. [#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. 
+   .. [#mi300x-past-60] Oracle Linux, Debian, and Azure Linux are supported only on AMD Instinct MI300X.
   .. [#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].
--- a/docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst
+++ b/docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst
@@ -10,22 +10,49 @@ 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 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 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:

-* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
+* `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_

-* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
+* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_

-* `PyTorch 2.7.0 (2.7.0a0+git3a58512) <https://github.com/pytorch/pytorch>`_
+* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
+
+* Tuning files (in CSV format)

 With this Docker image, you can quickly validate the expected inference
-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>`.
+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

 .. _vllm-benchmark-vllm:

@@ -64,9 +91,9 @@ MI300X accelerator with the prebuilt vLLM Docker image.

   .. code-block:: shell

-      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+      docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4

-Once the setup is complete, choose between two options to reproduce the
+Once setup is complete, you can choose between two options to reproduce the
 benchmark results:

 -  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
@@ -103,89 +130,45 @@ 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
 ----------------

-.. list-table::
-   :header-rows: 1
-   :widths: 2, 3
+.. hlist::
+   :columns: 3

-   * - Model name
-     - Tag
+   * ``pyt_vllm_llama-3.1-8b``

-   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
-     - ``pyt_vllm_llama-3.1-8b``
+   * ``pyt_vllm_llama-3.1-70b``

-   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
-     - ``pyt_vllm_llama-3.1-70b``
+   * ``pyt_vllm_llama-3.1-405b``

-   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
-     - ``pyt_vllm_llama-3.1-405b``
+   * ``pyt_vllm_llama-2-7b``

-   * - `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_llama-2-70b``

-   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
-     - ``pyt_vllm_llama-2-7b``
+   * ``pyt_vllm_mixtral-8x7b``

-   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
-     - ``pyt_vllm_llama-2-70b``
+   * ``pyt_vllm_mixtral-8x22b``

-   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
-     - ``pyt_vllm_mixtral-8x7b``
+   * ``pyt_vllm_mistral-7b``

-   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
-     - ``pyt_vllm_mixtral-8x22b``
+   * ``pyt_vllm_qwen2-7b``

-   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
-     - ``pyt_vllm_mistral-7b``
+   * ``pyt_vllm_qwen2-72b``

-   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
-     - ``pyt_vllm_qwen2-7b``
+   * ``pyt_vllm_jais-13b``

-   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
-     - ``pyt_vllm_qwen2-72b``
+   * ``pyt_vllm_jais-30b``

-   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
-     - ``pyt_vllm_jais-13b``
+   * ``pyt_vllm_llama-3.1-8b_fp8``

-   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
-     - ``pyt_vllm_jais-30b``
+   * ``pyt_vllm_llama-3.1-70b_fp8``

-   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
-     - ``pyt_vllm_dbrx-instruct``
+   * ``pyt_vllm_llama-3.1-405b_fp8``

-   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
-     - ``pyt_vllm_gemma-2-27b``
+   * ``pyt_vllm_mixtral-8x7b_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``
+   * ``pyt_vllm_mixtral-8x22b_fp8``

 .. _vllm-benchmark-standalone:

@@ -198,8 +181,8 @@ snippet.

 .. code-block::

-   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
+   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

 In the Docker container, clone the ROCm MAD repository and navigate to the
 benchmark scripts directory at ``~/MAD/scripts/vllm``.
@@ -241,8 +224,8 @@ See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.

 .. _vllm-benchmark-standalone-options:

-Options and available models
----------------------------
+Options
+-------

 .. list-table::
   :header-rows: 1
@@ -265,100 +248,72 @@ Options and available models
     - Measure both throughput and latency

   * - ``$model_repo``
-     - ``meta-llama/Llama-3.1-8B-Instruct``
-     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
+     - Llama 3.1 8B

   * - (``float16``)
-     - ``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-3.1-70B-Instruct``
+     - Llama 3.1 70B

   * -
-     - ``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/Meta-Llama-3.1-405B-Instruct``
+     - Llama 3.1 405B

   * -
     - ``meta-llama/Llama-2-7b-chat-hf``
-     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+     - Llama 2 7B

   * -
     - ``meta-llama/Llama-2-70b-chat-hf``
-     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+     - Llama 2 70B

   * -
     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
-     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+     - Mixtral 8x7B

   * -
     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
-     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+     - Mixtral 8x22B

   * -
     - ``mistralai/Mistral-7B-Instruct-v0.3``
-     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+     - Mixtral 7B

   * -
     - ``Qwen/Qwen2-7B-Instruct``
-     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+     - Qwen2 7B

   * -
     - ``Qwen/Qwen2-72B-Instruct``
-     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+     - Qwen2 72B

   * -
     - ``core42/jais-13b-chat``
-     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+     - JAIS 13B

   * -
     - ``core42/jais-30b-chat-v3``
-     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
-
-   * -
-     - ``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>`_
+     - JAIS 30B

   * - ``$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>`_
+     - ``amd/Meta-Llama-3.1-8B-Instruct-FP8-KV``
+     - Llama 3.1 8B

   * - (``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/Meta-Llama-3.1-70B-Instruct-FP8-KV``
+     - Llama 3.1 70B
+
+   * -
+     - ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
+     - Llama 3.1 405B

   * -
     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
-     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
+     - Mixtral 8x7B

   * -
     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
-     - `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>`_
+     - Mixtral 8x22B

   * - ``$num_gpu``
     - 1 or 8
@@ -380,34 +335,34 @@ options and their descriptions.
 Example 1: latency benchmark
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Use this command to benchmark the latency of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
+Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.

 .. code-block::

-   ./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
+   ./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

 Find the latency reports at:

- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``

- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_latency_report.csv``
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_latency_report.csv``

 Example 2: throughput benchmark
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

-Use this command to benchmark the throughput of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
+Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.

 .. code-block:: shell

-   ./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
+   ./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

 Find the throughput reports at:

- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``

- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_throughput_report.csv``
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_throughput_report.csv``

 .. raw:: html

@@ -439,7 +394,7 @@ 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:`Running models from Hugging Face <hugging-face-models>`.
+  :doc:`Using ROCm for AI <../index>`.

 - To learn how to optimize inference on LLMs, see
  :doc:`Inference optimization <../inference-optimization/index>`.
@@ -447,32 +402,6 @@ Further reading
 - To learn how to fine-tune LLMs, see
  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.

-Previous versions
-=================
+- 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>`_.

-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>`_
--- a/docs/reference/gpu-arch-specs.rst
+++ b/docs/reference/gpu-arch-specs.rst
@@ -32,8 +32,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - L1 Instruction Cache (KiB)
          - VGPR File (KiB)
          - SGPR File (KiB)
-          - GFXIP Major version
-          - GFXIP Minor version
        *
          - MI325X
          - CDNA3
@@ -49,8 +47,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 64 per 2 CUs
          - 512
          - 12.5
-          - 9
-          - 4
        *
          - MI300X
          - CDNA3
@@ -66,8 +62,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 64 per 2 CUs
          - 512
          - 12.5
-          - 9
-          - 4
        *
          - MI300A
          - CDNA3
@@ -83,8 +77,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 64 per 2 CUs
          - 512
          - 12.5
-          - 9
-          - 4
        *
          - MI250X
          - CDNA2
@@ -100,8 +92,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 2 CUs
          - 512
          - 12.5
-          - 9
-          - 0
        *
          - MI250
          - CDNA2
@@ -117,8 +107,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 2 CUs
          - 512
          - 12.5
-          - 9
-          - 0
        *
          - MI210
          - CDNA2
@@ -134,8 +122,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 2 CUs
          - 512
          - 12.5
-          - 9
-          - 0
        *
          - MI100
          - CDNA
@@ -151,8 +137,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256 VGPR and 256 AccVGPR
          - 12.5
-          - 9
-          - 0
        *
          - MI60
          - GCN5.1
@@ -168,8 +152,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256
          - 12.5
-          - 9
-          - 0
        *
          - MI50 (32GB)
          - GCN5.1
@@ -185,8 +167,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256
          - 12.5
-          - 9
-          - 0
        *
          - MI50 (16GB)
          - GCN5.1
@@ -202,8 +182,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256
          - 12.5
-          - 9
-          - 0
        *
          - MI25
          - GCN5.0
@@ -219,8 +197,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256
          - 12.5
-          - 9
-          - 0
        *
          - MI8
          - GCN3.0
@@ -236,8 +212,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 4 CUs
          - 256
          - 12.5
-          - 8
-          - 0
        *
          - MI6
          - GCN4.0
@@ -253,8 +227,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 4 CUs
          - 256
          - 12.5
-          - 8
-          - 0

  .. tab-item:: AMD Radeon PRO GPUs

@@ -266,7 +238,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - Model
          - Architecture
          - LLVM target name
-
          - VRAM (GiB)
          - Compute Units
          - Wavefront Size
@@ -279,8 +250,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - L0 Instruction Cache (KiB)
          - VGPR File (KiB)
          - SGPR File (KiB)
-          - GFXIP Major version
-          - GFXIP Minor version
        *
          - Radeon PRO V710
          - RDNA3
@@ -297,8 +266,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon PRO W7900 Dual Slot
          - RDNA3
@@ -315,8 +282,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon PRO W7900
          - RDNA3
@@ -333,8 +298,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon PRO W7800
          - RDNA3
@@ -351,8 +314,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon PRO W7700
          - RDNA3
@@ -369,8 +330,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon PRO W6800
          - RDNA2
@@ -387,8 +346,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon PRO W6600
          - RDNA2
@@ -405,8 +362,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon PRO V620
          - RDNA2
@@ -423,8 +378,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon Pro W5500
          - RDNA
@@ -441,8 +394,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 20
-          - 10
-          - 1
        *
          - Radeon Pro VII
          - GCN5.1
@@ -459,8 +410,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256
          - 12.5
-          - 9
-          - 0

  .. tab-item:: AMD Radeon GPUs

@@ -484,8 +433,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - L0 Instruction Cache (KiB)
          - VGPR File (KiB)
          - SGPR File (KiB)
-          - GFXIP Major version
-          - GFXIP Minor version
        *
          - Radeon RX 7900 XTX
          - RDNA3
@@ -502,8 +449,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon RX 7900 XT
          - RDNA3
@@ -520,8 +465,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon RX 7900 GRE
          - RDNA3
@@ -538,8 +481,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon RX 7800 XT
          - RDNA3
@@ -556,8 +497,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon RX 7700 XT
          - RDNA3
@@ -574,8 +513,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 768
          - 16
-          - 11
-          - 0
        *
          - Radeon RX 7600
          - RDNA3
@@ -592,8 +529,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 11
-          - 0
        *
          - Radeon RX 6950 XT
          - RDNA2
@@ -610,8 +545,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6900 XT
          - RDNA2
@@ -628,8 +561,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6800 XT
          - RDNA2
@@ -646,8 +577,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6800
          - RDNA2
@@ -664,8 +593,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6750 XT
          - RDNA2
@@ -682,8 +609,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6700 XT
          - RDNA2
@@ -700,8 +625,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6700
          - RDNA2
@@ -718,8 +641,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6650 XT
          - RDNA2
@@ -736,8 +657,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6600 XT
          - RDNA2
@@ -754,8 +673,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon RX 6600
          - RDNA2
@@ -772,8 +689,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 512
          - 16
-          - 10
-          - 3
        *
          - Radeon VII
          - GCN5.1
@@ -790,14 +705,12 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32 per 3 CUs
          - 256
          - 12.5
-          - 9
-          - 0

 Glossary
 ========

 For more information about the terms used, see the
-:ref:`specific documents and guides <gpu-arch-documentation>`, or
+:ref:`specific documents and guides <gpu-arch-documentation>`, or 
 :doc:`Understanding the HIP programming model<hip:understand/programming_model>`.

 **LLVM target name**
@@ -887,26 +800,6 @@ Purpose Vector Registers, used specifically in matrix instructions.
 Size of the Scalar General Purpose Register (SGPR) file. Holds data used in
 scalar instructions.

-**GFXIP**
-
-GFXIP (Graphics IP) is a versioning system used by AMD to identify the GPU
-architecture and its instruction set. It helps categorize different generations
-of GPUs and their feature sets.
-
-**GFXIP major version**
-
-Defines the GPU's core instruction set and architecture, which determines
-compatibility with software stacks such as HIP and OpenCL. For example, a GFXIP
-11 major version corresponds to the RDNA 3 (Navi 3x) architecture, influencing
-driver support and available compute features.
-
-**GFXIP minor version**
-
-Represents specific variations within a GFXIP major version and affects feature sets,
-optimizations, and driver behavior in software stacks such as HIP and OpenCL. Different
-GPU models within the same major version can have unique capabilities, impacting
-performance and supported instructions.
-
 **GCD**

 Graphics Compute Die.
--- a/docs/sphinx/requirements.txt
+++ b/docs/sphinx/requirements.txt
@@ -37,7 +37,7 @@ click==8.1.7
    #   sphinx-external-toc
 comm==0.2.2
    # via ipykernel
-cryptography==44.0.1
+cryptography==43.0.3
    # via pyjwt
 debugpy==1.8.12
    # via ipykernel