Create rocm-7.0.2.xml

7.0.2 GA update
Update vLLM doc for 10/6 release and bump rocm-docs-core to 1.26.0 (#5481 )
2026-01-09 22:58:17 -05:00 · 2025-10-10 11:59:08 +05:30 · 2025-10-10 11:57:38 +05:30 · 2025-10-08 16:23:40 -04:00 · 2025-10-08 15:05:11 -04:00 · 2025-10-08 14:47:44 -04:00
19 changed files with 1224 additions and 310 deletions
--- a/.azuredevops/components/hipTensor.yml
+++ b/.azuredevops/components/hipTensor.yml
@@ -77,6 +77,7 @@ jobs:
        extraBuildFlags: >-
          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/llvm
          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
          -DCMAKE_BUILD_TYPE=Release
          -DHIPTENSOR_BUILD_TESTS=ON
--- a/.azuredevops/components/rocm-examples.yml
+++ b/.azuredevops/components/rocm-examples.yml
@@ -37,8 +37,10 @@ parameters:
    - llvm-project
    - rocBLAS
    - rocFFT
+    - rocJPEG
    - rocPRIM
    - rocprofiler-register
+    - rocprofiler-sdk
    - ROCR-Runtime
    - rocRAND
    - rocSOLVER
@@ -65,7 +67,9 @@ parameters:
    - rocFFT
    - rocminfo
    - rocPRIM
+    - rocJPEG
    - rocprofiler-register
+    - rocprofiler-sdk
    - ROCR-Runtime
    - rocRAND
    - rocSOLVER
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -313,6 +313,7 @@ Mooncake
 Mpops
 Multicore
 Multithreaded
+MXFP
 MyEnvironment
 MyST
 NANOO
@@ -713,6 +714,7 @@ githooks
 github
 globals
 gnupg
+gpu
 grayscale
 gx
 gzip
@@ -767,6 +769,7 @@ invariants
 invocating
 ipo
 jax
+json
 kdb
 kfd
 kv
@@ -967,6 +970,7 @@ tabindex
 targetContainer
 td
 tensorfloat
+tf
 th
 tokenization
 tokenize
@@ -979,6 +983,7 @@ toolset
 toolsets
 torchtitan
 torchvision
+tp
 tqdm
 tracebacks
 txt
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,9 +4,13 @@ This page is a historical overview of changes made to ROCm components. This
 consolidated changelog documents key modifications and improvements across
 different versions of the ROCm software stack and its components.

+## ROCm 7.0.1
+
+ROCm 7.0.1 is a quality release that resolves the existing issue. There is no change in component from the previous ROCm 7.0.0 release. See the [ROCm 7.0.1 release notes](https://rocm.docs.amd.com/en/docs-7.0.1/about/release-notes.html#rocm-7-0-1-release-notes) for a complete overview of this release.
+
 ## ROCm 7.0.0

-See the [ROCm 7.0.0 release notes](https://rocm-stg.amd.com/en/latest/about/release-notes.html#rocm-7-0-0-release-notes)
+See the [ROCm 7.0.0 release notes](https://rocm.docs.amd.com/en/docs-7.0.0/about/release-notes.html#rocm-7-0-0-release-notes)
 for a complete overview of this release.

 ### **AMD SMI** (26.0.0)
--- a/RELEASE.md
+++ b/RELEASE.md
@@ -2748,7 +2748,7 @@ It's anticipated that ROCTracer, ROCProfiler, `rocprof`, and `rocprofv2` will re
 #### AMDGPU wavefront size compiler macro deprecation

 Access to the wavefront size as a compile-time constant via the `__AMDGCN_WAVEFRONT_SIZE`
-and `__AMDGCN_WAVEFRONT_SIZE__` macros are deprecated and will be disabled in a future release. In ROCm 7.0.0 `warpSize` is only available as a non-`constextpr` variable. You're encouraged to update your code if needed to ensure future compatibility.
+and `__AMDGCN_WAVEFRONT_SIZE__` macros are deprecated and will be disabled in a future release. In ROCm 7.0.0 `warpSize` is only available as a non-`constexpr` variable. You're encouraged to update your code if needed to ensure future compatibility.

 * The `__AMDGCN_WAVEFRONT_SIZE__` macro and `__AMDGCN_WAVEFRONT_SIZE` alias will be removed in an upcoming release.
  It is recommended to remove any use of this macro. For more information, see
--- a/default.xml
+++ b/default.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-7.0.1"
+    <default revision="refs/tags/rocm-7.0.2"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
@@ -41,7 +41,6 @@
    <project groups="mathlibs" name="MIVisionX" />
    <project groups="mathlibs" name="ROCmValidationSuite" />
    <project groups="mathlibs" name="composable_kernel" />
-    <project groups="mathlibs" name="hipSOLVER" />
    <project groups="mathlibs" name="hipTensor" />
    <project groups="mathlibs" name="hipfort" />
    <project groups="mathlibs" name="rccl" />
@@ -57,7 +56,6 @@
    <project groups="mathlibs" name="rocm-libraries" />
    <project groups="mathlibs" name="rocPyDecode" />
    <project groups="mathlibs" name="rocSHMEM" />
-    <project groups="mathlibs" name="rocSOLVER" />
    <project groups="mathlibs" name="rocWMMA" />
    <project groups="mathlibs" name="rocm-cmake" />
    <project groups="mathlibs" name="rpp" />
--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/docs/compatibility/compatibility-matrix-historical-6.0.csv
@@ -30,8 +30,8 @@ ROCm Version,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6
      ,gfx908 [#mi100-os-past-60]_,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
 ,,,,,,,,,,,,,,,,,,,
      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
+      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/docs/compatibility/compatibility-matrix.rst
@@ -55,8 +55,8 @@ compatibility and system requirements.
      ,gfx908 [#mi100-os]_,gfx908,gfx908
      ,,,
      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 2.1, 2.0, 1.13"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1"
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 2.1, 2.0, 1.13"
+      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1, 2.17.1 [#tf-mi350]_","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1"
      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.6.0,0.4.35,0.4.31
      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat]_,N/A,N/A,85f95ae
      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,0.7.0
@@ -174,6 +174,7 @@ compatibility and system requirements.
 .. [#mi200x-os] **For ROCm 7.0.x** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
 .. [#mi100-os] **For ROCm 7.0.x** - AMD Instinct MI100 GPU (gfx908) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
 .. [#7700XT-OS] **Prior ROCm 7.0.0** - Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
+.. [#tf-mi350] TensorFlow 2.17.1 is not supported on AMD Instinct MI350 series GPUs. Use TensorFlow 2.19.1 or 2.18.1 with MI350 series GPUs instead.
 .. [#stanford-megatron-lm_compat] Stanford Megatron-LM is only supported on ROCm 6.3.0.
 .. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
 .. [#llama-cpp_compat] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
@@ -278,6 +279,7 @@ Expand for full historical view of:
   .. [#mi300_610-past-60] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
   .. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
   .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
+   .. [#tf-mi350-past-60] TensorFlow 2.17.1 is not supported on AMD Instinct MI350 series GPUs. Use TensorFlow 2.19.1 or 2.18.1 with MI350 series GPUs instead.
   .. [#verl_compat-past-60] verl is only supported on ROCm 6.2.0.
   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is only supported on ROCm 6.3.0.
   .. [#dgl_compat-past-60] DGL is only supported on ROCm 6.4.0.
--- a/docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20250909-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20250909-benchmark-models.yaml
@@ -0,0 +1,188 @@
+dockers:
+  - pull_tag: rocm/vllm:rocm6.4.1_vllm_0.10.1_20250909
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.10.1_20250909/images/sha256-1113268572e26d59b205792047bea0e61e018e79aeadceba118b7bf23cb3715c
+    components:
+      ROCm: 6.4.1
+      vLLM: 0.10.1 (0.10.1rc2.dev409+g0b6bf6691.rocm641)
+      PyTorch: 2.7.0+gitf717b2a
+      hipBLASLt: 0.15
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 3.1 8B
+      mad_tag: pyt_vllm_llama-3.1-8b
+      model_repo: meta-llama/Llama-3.1-8B-Instruct
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: float16
+      config:
+        tp: 1
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+    - model: Llama 3.1 70B
+      mad_tag: pyt_vllm_llama-3.1-70b
+      model_repo: meta-llama/Llama-3.1-70B-Instruct
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+      precision: float16
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+    - model: Llama 3.1 405B
+      mad_tag: pyt_vllm_llama-3.1-405b
+      model_repo: meta-llama/Llama-3.1-405B-Instruct
+      url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+      precision: float16
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+    - model: Llama 2 70B
+      mad_tag: pyt_vllm_llama-2-70b
+      model_repo: meta-llama/Llama-2-70b-chat-hf
+      url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+      precision: float16
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 4096
+        max_num_batched_tokens: 4096
+        max_model_len: 4096
+    - model: Llama 3.1 8B FP8
+      mad_tag: pyt_vllm_llama-3.1-8b_fp8
+      model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+      url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+      precision: float8
+      config:
+        tp: 1
+        dtype: auto
+        kv_cache_dtype: fp8
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+    - model: Llama 3.1 70B FP8
+      mad_tag: pyt_vllm_llama-3.1-70b_fp8
+      model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
+      url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
+      precision: float8
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: fp8
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+    - model: Llama 3.1 405B FP8
+      mad_tag: pyt_vllm_llama-3.1-405b_fp8
+      model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+      url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+      precision: float8
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: fp8
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+  - group: Mistral AI
+    tag: mistral
+    models:
+    - model: Mixtral MoE 8x7B
+      mad_tag: pyt_vllm_mixtral-8x7b
+      model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+      url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+      precision: float16
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 32768
+        max_num_batched_tokens: 32768
+        max_model_len: 8192
+    - model: Mixtral MoE 8x22B
+      mad_tag: pyt_vllm_mixtral-8x22b
+      model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+      url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+      precision: float16
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 65536
+        max_num_batched_tokens: 65536
+        max_model_len: 8192
+    - model: Mixtral MoE 8x7B FP8
+      mad_tag: pyt_vllm_mixtral-8x7b_fp8
+      model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+      url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+      precision: float8
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: fp8
+        max_seq_len_to_capture: 32768
+        max_num_batched_tokens: 32768
+        max_model_len: 8192
+    - model: Mixtral MoE 8x22B FP8
+      mad_tag: pyt_vllm_mixtral-8x22b_fp8
+      model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+      url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+      precision: float8
+      config:
+        tp: 8
+        dtype: auto
+        kv_cache_dtype: fp8
+        max_seq_len_to_capture: 65536
+        max_num_batched_tokens: 65536
+        max_model_len: 8192
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: QwQ-32B
+      mad_tag: pyt_vllm_qwq-32b
+      model_repo: Qwen/QwQ-32B
+      url: https://huggingface.co/Qwen/QwQ-32B
+      precision: float16
+      config:
+        tp: 1
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 131072
+        max_num_batched_tokens: 131072
+        max_model_len: 8192
+    - model: Qwen3 30B A3B
+      mad_tag: pyt_vllm_qwen3-30b-a3b
+      model_repo: Qwen/Qwen3-30B-A3B
+      url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+      precision: float16
+      config:
+        tp: 1
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 32768
+        max_num_batched_tokens: 32768
+        max_model_len: 8192
+  - group: Microsoft Phi
+    tag: phi
+    models:
+    - model: Phi-4
+      mad_tag: pyt_vllm_phi-4
+      model_repo: microsoft/phi-4
+      url: https://huggingface.co/microsoft/phi-4
+      config:
+        tp: 1
+        dtype: auto
+        kv_cache_dtype: auto
+        max_seq_len_to_capture: 16384
+        max_num_batched_tokens: 16384
+        max_model_len: 8192
--- a/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
@@ -1,188 +1,316 @@
 dockers:
-  - pull_tag: rocm/vllm:rocm6.4.1_vllm_0.10.1_20250909
-    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.10.1_20250909/images/sha256-1113268572e26d59b205792047bea0e61e018e79aeadceba118b7bf23cb3715c
+  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5
    components:
-      ROCm: 6.4.1
-      vLLM: 0.10.1 (0.10.1rc2.dev409+g0b6bf6691.rocm641)
-      PyTorch: 2.7.0+gitf717b2a
-      hipBLASLt: 0.15
+      ROCm: 7.0.0
+      vLLM: 0.10.2 (0.11.0rc2.dev160+g790d22168.rocm700)
+      PyTorch: 2.9.0a0+git1c57644
+      hipBLASLt: 1.0.0
+    dockerfile:
+      commit: 790d22168820507f3105fef29596549378cfe399
 model_groups:
  - group: Meta Llama
    tag: llama
    models:
-    - model: Llama 3.1 8B
-      mad_tag: pyt_vllm_llama-3.1-8b
-      model_repo: meta-llama/Llama-3.1-8B-Instruct
-      url: https://huggingface.co/meta-llama/Llama-3.1-8B
-      precision: float16
-      config:
-        tp: 1
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
-    - model: Llama 3.1 70B
-      mad_tag: pyt_vllm_llama-3.1-70b
-      model_repo: meta-llama/Llama-3.1-70B-Instruct
-      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
-      precision: float16
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
-    - model: Llama 3.1 405B
-      mad_tag: pyt_vllm_llama-3.1-405b
-      model_repo: meta-llama/Llama-3.1-405B-Instruct
-      url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
-      precision: float16
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
-    - model: Llama 2 70B
-      mad_tag: pyt_vllm_llama-2-70b
-      model_repo: meta-llama/Llama-2-70b-chat-hf
-      url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
-      precision: float16
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 4096
-        max_num_batched_tokens: 4096
-        max_model_len: 4096
-    - model: Llama 3.1 8B FP8
-      mad_tag: pyt_vllm_llama-3.1-8b_fp8
-      model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
-      url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
-      precision: float8
-      config:
-        tp: 1
-        dtype: auto
-        kv_cache_dtype: fp8
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
-    - model: Llama 3.1 70B FP8
-      mad_tag: pyt_vllm_llama-3.1-70b_fp8
-      model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
-      url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
-      precision: float8
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: fp8
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
-    - model: Llama 3.1 405B FP8
-      mad_tag: pyt_vllm_llama-3.1-405b_fp8
-      model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
-      url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
-      precision: float8
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: fp8
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
+      - model: Llama 2 70B
+        mad_tag: pyt_vllm_llama-2-70b
+        model_repo: meta-llama/Llama-2-70b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 4096
+          max_model_len: 4096
+      - model: Llama 3.1 8B
+        mad_tag: pyt_vllm_llama-3.1-8b
+        model_repo: meta-llama/Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 8B FP8
+        mad_tag: pyt_vllm_llama-3.1-8b_fp8
+        model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B
+        mad_tag: pyt_vllm_llama-3.1-405b
+        model_repo: meta-llama/Llama-3.1-405B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B FP8
+        mad_tag: pyt_vllm_llama-3.1-405b_fp8
+        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B MXFP4
+        mad_tag: pyt_vllm_llama-3.1-405b_fp4
+        model_repo: amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B
+        mad_tag: pyt_vllm_llama-3.3-70b
+        model_repo: meta-llama/Llama-3.3-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B FP8
+        mad_tag: pyt_vllm_llama-3.3-70b_fp8
+        model_repo: amd/Llama-3.3-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B MXFP4
+        mad_tag: pyt_vllm_llama-3.3-70b_fp4
+        model_repo: amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 4 Scout 17Bx16E
+        mad_tag: pyt_vllm_llama-4-scout-17b-16e
+        model_repo: meta-llama/Llama-4-Scout-17B-16E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E FP8
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e_fp8
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek R1 0528 FP8
+        mad_tag: pyt_vllm_deepseek-r1
+        model_repo: deepseek-ai/DeepSeek-R1-0528
+        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_seqs: 1024
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: OpenAI GPT OSS
+    tag: gpt-oss
+    models:
+      - model: GPT OSS 20B
+        mad_tag: pyt_vllm_gpt-oss-20b
+        model_repo: openai/gpt-oss-20b
+        url: https://huggingface.co/openai/gpt-oss-20b
+        precision: bfloat16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+      - model: GPT OSS 120B
+        mad_tag: pyt_vllm_gpt-oss-120b
+        model_repo: openai/gpt-oss-120b
+        url: https://huggingface.co/openai/gpt-oss-120b
+        precision: bfloat16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
  - group: Mistral AI
    tag: mistral
    models:
-    - model: Mixtral MoE 8x7B
-      mad_tag: pyt_vllm_mixtral-8x7b
-      model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
-      url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
-      precision: float16
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 32768
-        max_num_batched_tokens: 32768
-        max_model_len: 8192
-    - model: Mixtral MoE 8x22B
-      mad_tag: pyt_vllm_mixtral-8x22b
-      model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
-      url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
-      precision: float16
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 65536
-        max_num_batched_tokens: 65536
-        max_model_len: 8192
-    - model: Mixtral MoE 8x7B FP8
-      mad_tag: pyt_vllm_mixtral-8x7b_fp8
-      model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
-      url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
-      precision: float8
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: fp8
-        max_seq_len_to_capture: 32768
-        max_num_batched_tokens: 32768
-        max_model_len: 8192
-    - model: Mixtral MoE 8x22B FP8
-      mad_tag: pyt_vllm_mixtral-8x22b_fp8
-      model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
-      url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
-      precision: float8
-      config:
-        tp: 8
-        dtype: auto
-        kv_cache_dtype: fp8
-        max_seq_len_to_capture: 65536
-        max_num_batched_tokens: 65536
-        max_model_len: 8192
+      - model: Mixtral MoE 8x7B
+        mad_tag: pyt_vllm_mixtral-8x7b
+        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Mixtral MoE 8x7B FP8
+        mad_tag: pyt_vllm_mixtral-8x7b_fp8
+        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Mixtral MoE 8x22B
+        mad_tag: pyt_vllm_mixtral-8x22b
+        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+      - model: Mixtral MoE 8x22B FP8
+        mad_tag: pyt_vllm_mixtral-8x22b_fp8
+        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
  - group: Qwen
    tag: qwen
    models:
-    - model: QwQ-32B
-      mad_tag: pyt_vllm_qwq-32b
-      model_repo: Qwen/QwQ-32B
-      url: https://huggingface.co/Qwen/QwQ-32B
-      precision: float16
-      config:
-        tp: 1
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 131072
-        max_num_batched_tokens: 131072
-        max_model_len: 8192
-    - model: Qwen3 30B A3B
-      mad_tag: pyt_vllm_qwen3-30b-a3b
-      model_repo: Qwen/Qwen3-30B-A3B
-      url: https://huggingface.co/Qwen/Qwen3-30B-A3B
-      precision: float16
-      config:
-        tp: 1
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 32768
-        max_num_batched_tokens: 32768
-        max_model_len: 8192
+      - model: Qwen3 8B
+        mad_tag: pyt_vllm_qwen3-8b
+        model_repo: Qwen/Qwen3-8B
+        url: https://huggingface.co/Qwen/Qwen3-8B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 32B
+        mad_tag: pyt_vllm_qwen3-32b
+        model_repo: Qwen/Qwen3-32b
+        url: https://huggingface.co/Qwen/Qwen3-32B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B
+        mad_tag: pyt_vllm_qwen3-30b-a3b
+        model_repo: Qwen/Qwen3-30B-A3B
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B FP8
+        mad_tag: pyt_vllm_qwen3-30b-a3b_fp8
+        model_repo: Qwen/Qwen3-30B-A3B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B
+        mad_tag: pyt_vllm_qwen3-235b-a22b
+        model_repo: Qwen/Qwen3-235B-A22B
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B FP8
+        mad_tag: pyt_vllm_qwen3-235b-a22b_fp8
+        model_repo: Qwen/Qwen3-235B-A22B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
  - group: Microsoft Phi
    tag: phi
    models:
-    - model: Phi-4
-      mad_tag: pyt_vllm_phi-4
-      model_repo: microsoft/phi-4
-      url: https://huggingface.co/microsoft/phi-4
-      config:
-        tp: 1
-        dtype: auto
-        kv_cache_dtype: auto
-        max_seq_len_to_capture: 16384
-        max_num_batched_tokens: 16384
-        max_model_len: 8192
+      - model: Phi-4
+        mad_tag: pyt_vllm_phi-4
+        model_repo: microsoft/phi-4
+        url: https://huggingface.co/microsoft/phi-4
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 16384
+          max_model_len: 8192
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.1-20250909.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.1-20250909.rst
@@ -0,0 +1,448 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker-909:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20250909-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   The `ROCm vLLM Docker <{{ docker.docker_hub_url }}>`_ image offers
+   a prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
+   accelerators and includes the following components:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+With this Docker image, you can quickly test the :ref:`expected
+inference performance numbers <vllm-benchmark-performance-measurements-909>` for
+MI300X series accelerators.
+
+What's new
+==========
+
+The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <vllm-history>`.
+
+* Upgraded to vLLM v0.10.1.
+
+* Set ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1`` by default for better performance.
+
+* Set ``VLLM_ROCM_USE_AITER_RMSNORM=0`` by default to avoid various issues with torch compile.
+
+.. _vllm-benchmark-supported-models-909:
+
+Supported models
+================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20250909-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   .. _vllm-benchmark-available-models-909:
+
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+   .. _vllm-benchmark-vllm-909:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.mad_tag }}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+      {% if model.precision == "float8" and model.model_repo.startswith("amd") %}
+         This model uses FP8 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD accelerators.
+      {% endif %}
+
+      {% endfor %}
+   {% endfor %}
+
+.. _vllm-benchmark-performance-measurements-909:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+page provides reference throughput and serving measurements for inferencing popular AI models.
+
+.. important::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   only reflects the latest version of this inference benchmarking environment.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20250909-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   Pull the Docker image
+   =====================
+
+   Download the `ROCm vLLM Docker image <{{ docker.docker_hub_url }}>`_.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad-909:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`vllm-benchmark-supported-models-909` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+               using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
+            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
+            and ``{{ model.mad_tag }}_serving.csv``.
+
+            Although the :ref:`available models
+            <vllm-benchmark-available-models-909>` are preconfigured to collect
+            offline throughput and online serving performance data, you can
+            also change the benchmarking parameters. See the standalone
+            benchmarking tab for more information.
+
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To enable it, include
+               the ``--tunableop on`` argument in your run.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the
+               performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            The following commands are optimized for {{ model.model }}.
+            See :ref:`vllm-benchmark-supported-models-909` to switch to another available model.
+
+            .. seealso::
+
+               For more information on configuration, see the `config files
+               <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__
+               in the MAD repository. Refer to the `vLLM engine <https://docs.vllm.ai/en/latest/configuration/engine_args.html#engineargs>`__
+               for descriptions of available configuration options
+               and `Benchmarking vLLM <https://github.com/vllm-project/vllm/blob/main/benchmarks/README.md>`__ for
+               additional benchmarking information.
+
+            .. rubric:: Launch the container
+
+            You can run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ docker.docker_hub_url }}>`_ as shown
+            in the following snippet.
+
+            .. code-block:: shell
+
+               docker pull {{ docker.pull_tag }}
+               docker run -it \
+                   --device=/dev/kfd \
+                   --device=/dev/dri \
+                   --group-add video \
+                   --shm-size 16G \
+                   --security-opt seccomp=unconfined \
+                   --security-opt apparmor=unconfined \
+                   --cap-add=SYS_PTRACE \
+                   -v $(pwd):/workspace \
+                   --env HUGGINGFACE_HUB_CACHE=/workspace \
+                   --name test \
+                   {{ docker.pull_tag }}
+
+            .. rubric:: Throughput command
+
+            Use the following command to start the throughput benchmark.
+
+            .. code-block:: shell
+
+               model={{ model.model_repo }}
+               tp={{ model.config.tp }}
+               num_prompts=1024
+               in=128
+               out=128
+               dtype={{ model.config.dtype }}
+               kv_cache_dtype={{ model.config.kv_cache_dtype }}
+               max_num_seqs=1024
+               max_seq_len_to_capture={{ model.config.max_seq_len_to_capture }}
+               max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
+               max_model_len={{ model.config.max_model_len }}
+
+               vllm bench throughput --model $model \
+                   -tp $tp \
+                   --num-prompts $num_prompts \
+                   --input-len $in \
+                   --output-len $out \
+                   --dtype $dtype \
+                   --kv-cache-dtype $kv_cache_dtype \
+                   --max-num-seqs $max_num_seqs \
+                   --max-seq-len-to-capture $max_seq_len_to_capture \
+                   --max-num-batched-tokens $max_num_batched_tokens \
+                   --max-model-len $max_model_len \
+                   --trust-remote-code \
+                   --output-json ${model}_throughput.json \
+                   --gpu-memory-utilization 0.9
+
+            .. rubric:: Serving command
+
+            1. Start the server using the following command:
+
+               .. code-block:: shell
+
+                  model={{ model.model_repo }}
+                  tp={{ model.config.tp }}
+                  dtype={{ model.config.dtype }}
+                  kv_cache_dtype={{ model.config.kv_cache_dtype }}
+                  max_num_seqs=256
+                  max_seq_len_to_capture={{ model.config.max_seq_len_to_capture }}
+                  max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
+                  max_model_len={{ model.config.max_model_len }}
+
+                  vllm serve $model \
+                      -tp $tp \
+                      --dtype $dtype \
+                      --kv-cache-dtype $kv_cache_dtype \
+                      --max-num-seqs $max_num_seqs \
+                      --max-seq-len-to-capture $max_seq_len_to_capture \
+                      --max-num-batched-tokens $max_num_batched_tokens \
+                      --max-model-len $max_model_len \
+                      --no-enable-prefix-caching \
+                      --swap-space 16 \
+                      --disable-log-requests \
+                      --trust-remote-code \
+                      --gpu-memory-utilization 0.9
+
+               Wait until the model has loaded and the server is ready to accept requests.
+
+            2. On another terminal on the same machine, run the benchmark:
+
+               .. code-block:: shell
+
+                  # Connect to the container
+                  docker exec -it test bash
+
+                  # Wait for the server to start
+                  until curl -s http://localhost:8000/v1/models; do sleep 30; done
+
+                  # Run the benchmark
+                  model={{ model.model_repo }}
+                  max_concurrency=1
+                  num_prompts=10
+                  in=128
+                  out=128
+                  vllm bench serve --model $model \
+                      --percentile-metrics "ttft,tpot,itl,e2el" \
+                      --dataset-name random \
+                      --ignore-eos \
+                      --max-concurrency $max_concurrency \
+                      --num-prompts $num_prompts \
+                      --random-input-len $in \
+                      --random-output-len $out \
+                      --trust-remote-code \
+                      --save-result \
+                      --result-filename ${model}_serving.json
+
+            .. note::
+
+               For improved performance with certain Mixture of Experts models, such as Mixtral 8x22B,
+               try adding ``export VLLM_ROCM_USE_AITER=1`` to your commands.
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Advanced usage
+==============
+
+For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+see the developer's guide at `<https://github.com/ROCm/vllm/blob/documentation/docs/dev-docker/README.md>`__.
+
+Reproducing the Docker image
+----------------------------
+
+To reproduce this ROCm/vLLM Docker image release, follow these steps:
+
+1. Clone the `vLLM repository <https://github.com/ROCm/vllm>`__.
+
+   .. code-block:: shell
+
+      git clone https://github.com/ROCm/vllm.git
+
+2. Checkout the specific release commit.
+
+   .. code-block:: shell
+
+      cd vllm
+      git checkout 6663000a391911eba96d7864a26ac42b07f6ef29
+
+3. Build the Docker image. Replace ``vllm-rocm`` with your desired image tag.
+
+   .. code-block:: shell
+
+      docker build -f docker/Dockerfile.rocm -t vllm-rocm .
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+  a brief introduction to vLLM and optimization strategies.
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-history.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-history.rst
@@ -7,7 +7,7 @@ vLLM inference performance testing version history
 This table lists previous versions of the ROCm vLLM inference Docker image for
 inference performance testing. For detailed information about available models
 for benchmarking, see the version-specific documentation. You can find tagged
-previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.10.1_20250909/images/sha256-1113268572e26d59b205792047bea0e61e018e79aeadceba118b7bf23cb3715c>`__.
+previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/vllm/tags>`__.

 .. list-table::
   :header-rows: 1
@@ -16,14 +16,23 @@ previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.
     - Components
     - Resources

-   * - ``rocm/vllm:rocm6.4.1_vllm_0.10.1_20250909``
+   * - ``rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006``
       (latest)
+     -
+       * ROCm 7.0.0
+       * vLLM 0.10.2
+       * PyTorch 2.9.0
+     -
+       * :doc:`Documentation <../vllm>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5>`__
+
+   * - ``rocm/vllm:rocm6.4.1_vllm_0.10.1_20250909``
     -
       * ROCm 6.4.1
       * vLLM 0.10.1
       * PyTorch 2.7.0
     -
-       * :doc:`Documentation <../vllm>`
+       * :doc:`Documentation <vllm-0.10.1-20250909>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.10.1_20250909/images/sha256-1113268572e26d59b205792047bea0e61e018e79aeadceba118b7bf23cb3715c>`__

   * - ``rocm/vllm:rocm6.4.1_vllm_0.10.0_20250812``
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
@@ -6,45 +6,63 @@
 vLLM inference performance testing
 **********************************

-.. _vllm-benchmark-unified-docker-909:
+.. _vllm-benchmark-unified-docker-930:

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml

   {% set docker = data.dockers[0] %}

-   The `ROCm vLLM Docker <{{ docker.docker_hub_url }}>`_ image offers
-   a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series GPUs. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   GPUs and includes the following components:
+   The `ROCm vLLM Docker <{{ docker.docker_hub_url }}>`_ image offers a
+   prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI355X, MI350X, MI325X and MI300X
+   GPUs. This ROCm vLLM Docker image integrates vLLM and PyTorch tailored
+   specifically for AMD data center GPUs and includes the following components:

-   .. list-table::
-      :header-rows: 1
+   .. tab-set::

-      * - Software component
-        - Version
+      .. tab-item:: {{ docker.pull_tag }}

-      {% for component_name, component_version in docker.components.items() %}
-      * - {{ component_name }}
-        - {{ component_version }}
-      {% endfor %}
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}

 With this Docker image, you can quickly test the :ref:`expected
-inference performance numbers <vllm-benchmark-performance-measurements-909>` for
-MI300X series GPUs.
+inference performance numbers <vllm-benchmark-performance-measurements-930>` for
+AMD Instinct GPUs.

 What's new
 ==========

 The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <previous-versions/vllm-history>`.

-* Upgraded to vLLM v0.10.1.
+* Added support for AMD Instinct MI355X and MI350X GPUs.

-* Set ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1`` by default for better performance.
+* Added support and benchmarking instructions for the following models. See :ref:`vllm-benchmark-supported-models-930`.

-* Set ``VLLM_ROCM_USE_AITER_RMSNORM=0`` by default to avoid various issues with torch compile.
+  * Llama 4 Scout and Maverick

-.. _vllm-benchmark-supported-models-909:
+  * DeepSeek R1 0528 FP8
+
+  * MXFP4 models (MI355X and MI350X only): Llama 3.3 70B MXFP4 and Llama 3.1 405B MXFP4
+
+  * GPT OSS 20B and 120B
+
+  * Qwen 3 32B, 30B-A3B, and 235B-A22B
+
+* Removed the deprecated ``--max-seq-len-to-capture`` flag.
+
+* ``--gpu-memory-utilization`` is now configurable via the `configuration files
+  <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__ in the MAD
+  repository.
+
+.. _vllm-benchmark-supported-models-930:

 Supported models
 ================
@@ -54,11 +72,12 @@ Supported models
   {% set docker = data.dockers[0] %}
   {% set model_groups = data.model_groups %}

-   .. _vllm-benchmark-available-models-909:
+   .. _vllm-benchmark-available-models-930:

   The following models are supported for inference performance benchmarking
   with vLLM and ROCm. Some instructions, commands, and recommendations in this
-   documentation might vary by model -- select one to get started.
+   documentation might vary by model -- select one to get started. MXFP4 models
+   are only supported on MI355X and MI350X GPUs.

   .. raw:: html

@@ -67,7 +86,7 @@ Supported models
            <div class="col-2 me-1 px-2 model-param-head">Model</div>
            <div class="row col-10 pe-0">
      {% for model_group in model_groups %}
-               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
      {% endfor %}
            </div>
         </div>
@@ -89,13 +108,20 @@ Supported models
         </div>
      </div>

-   .. _vllm-benchmark-vllm-909:
+   .. _vllm-benchmark-vllm-930:

   {% for model_group in model_groups %}
      {% for model in model_group.models %}

   .. container:: model-doc {{ model.mad_tag }}

+
+      {% if model.precision == "float4" %}
+      .. important::
+
+         MXFP4 is supported only on MI355X and MI350X GPUs.
+      {% endif %}
+
      .. note::

         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
@@ -103,11 +129,14 @@ Supported models
      {% if model.precision == "float8" and model.model_repo.startswith("amd") %}
         This model uses FP8 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD GPUs.
      {% endif %}
+      {% if model.precision == "float4" and model.model_repo.startswith("amd") %}
+         This model uses FP4 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD GPUs.
+      {% endif %}

      {% endfor %}
   {% endfor %}

-.. _vllm-benchmark-performance-measurements-909:
+.. _vllm-benchmark-performance-measurements-930:

 Performance measurements
 ========================
@@ -121,7 +150,7 @@ page provides reference throughput and serving measurements for inferencing popu
   The performance data presented in
   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
   only reflects the latest version of this inference benchmarking environment.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct GPUs or ROCm software.

 System validation
 =================
@@ -138,13 +167,12 @@ To test for optimal performance, consult the recommended :ref:`System health ben
 <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
 system's configuration.

+Pull the Docker image
+=====================
+
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml

   {% set docker = data.dockers[0] %}
-   {% set model_groups = data.model_groups %}
-
-   Pull the Docker image
-   =====================

   Download the `ROCm vLLM Docker image <{{ docker.docker_hub_url }}>`_.
   Use the following command to pull the Docker image from Docker Hub.
@@ -153,13 +181,18 @@ system's configuration.

      docker pull {{ docker.pull_tag }}

-   Benchmarking
-   ============
+Benchmarking
+============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}

   Once the setup is complete, choose between two options to reproduce the
   benchmark results:

-   .. _vllm-benchmark-mad-909:
+   .. _vllm-benchmark-mad-930:

   {% for model_group in model_groups %}
      {% for model in model_group.models %}
@@ -171,7 +204,7 @@ system's configuration.
         .. tab-item:: MAD-integrated benchmarking

            The following run command is tailored to {{ model.model }}.
-            See :ref:`vllm-benchmark-supported-models-909` to switch to another available model.
+            See :ref:`vllm-benchmark-supported-models-930` to switch to another available model.

            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
               directory and install the required packages on the host machine.
@@ -182,8 +215,9 @@ system's configuration.
                  cd MAD
                  pip install -r requirements.txt

-            2. Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
-               using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
+            2. On the host machine, use this command to run the performance benchmark test on
+               the `{{model.model}} <{{ model.url }}>`_ model using one node with the
+               :literal:`{{model.precision}}` data type.

               .. code-block:: shell

@@ -191,8 +225,7 @@ system's configuration.
                  madengine run \
                      --tags {{model.mad_tag}} \
                      --keep-model-dir \
-                      --live-output \
-                      --timeout 28800
+                      --live-output

            MAD launches a Docker container with the name
            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
@@ -200,7 +233,7 @@ system's configuration.
            and ``{{ model.mad_tag }}_serving.csv``.

            Although the :ref:`available models
-            <vllm-benchmark-available-models-909>` are preconfigured to collect
+            <vllm-benchmark-available-models-930>` are preconfigured to collect
            offline throughput and online serving performance data, you can
            also change the benchmarking parameters. See the standalone
            benchmarking tab for more information.
@@ -225,7 +258,7 @@ system's configuration.
         .. tab-item:: Standalone benchmarking

            The following commands are optimized for {{ model.model }}.
-            See :ref:`vllm-benchmark-supported-models-909` to switch to another available model.
+            See :ref:`vllm-benchmark-supported-models-930` to switch to another available model.

            .. seealso::

@@ -266,13 +299,12 @@ system's configuration.

               model={{ model.model_repo }}
               tp={{ model.config.tp }}
-               num_prompts=1024
-               in=128
-               out=128
-               dtype={{ model.config.dtype }}
+               num_prompts={{ model.config.num_prompts | default(1024) }}
+               in={{ model.config.in | default(128) }}
+               out={{ model.config.in | default(128) }}
+               dtype={{ model.config.dtype | default("auto") }}
               kv_cache_dtype={{ model.config.kv_cache_dtype }}
-               max_num_seqs=1024
-               max_seq_len_to_capture={{ model.config.max_seq_len_to_capture }}
+               max_num_seqs={{ model.config.max_num_seqs | default(1024) }}
               max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
               max_model_len={{ model.config.max_model_len }}

@@ -284,12 +316,11 @@ system's configuration.
                   --dtype $dtype \
                   --kv-cache-dtype $kv_cache_dtype \
                   --max-num-seqs $max_num_seqs \
-                   --max-seq-len-to-capture $max_seq_len_to_capture \
                   --max-num-batched-tokens $max_num_batched_tokens \
                   --max-model-len $max_model_len \
                   --trust-remote-code \
                   --output-json ${model}_throughput.json \
-                   --gpu-memory-utilization 0.9
+                   --gpu-memory-utilization {{ model.config.gpu_memory_utilization | default(0.9) }}

            .. rubric:: Serving command

@@ -302,7 +333,6 @@ system's configuration.
                  dtype={{ model.config.dtype }}
                  kv_cache_dtype={{ model.config.kv_cache_dtype }}
                  max_num_seqs=256
-                  max_seq_len_to_capture={{ model.config.max_seq_len_to_capture }}
                  max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
                  max_model_len={{ model.config.max_model_len }}

@@ -311,7 +341,6 @@ system's configuration.
                      --dtype $dtype \
                      --kv-cache-dtype $kv_cache_dtype \
                      --max-num-seqs $max_num_seqs \
-                      --max-seq-len-to-capture $max_seq_len_to_capture \
                      --max-num-batched-tokens $max_num_batched_tokens \
                      --max-model-len $max_model_len \
                      --no-enable-prefix-caching \
@@ -393,26 +422,31 @@ see the developer's guide at `<https://github.com/ROCm/vllm/blob/documentation/d
 Reproducing the Docker image
 ----------------------------

-To reproduce this ROCm/vLLM Docker image release, follow these steps:
+To reproduce this ROCm-enabled vLLM Docker image release, follow these steps:

-1. Clone the `vLLM repository <https://github.com/ROCm/vllm>`__.
-
-   .. code-block:: shell
-
-      git clone https://github.com/ROCm/vllm.git
-
-2. Checkout the specific release commit.
+1. Clone the `vLLM repository <https://github.com/vllm-project/vllm>`__.

   .. code-block:: shell

+      git clone https://github.com/vllm-project/vllm.git
      cd vllm
-      git checkout 6663000a391911eba96d7864a26ac42b07f6ef29

-3. Build the Docker image. Replace ``vllm-rocm`` with your desired image tag.
+2. Use the following command to build the image directly from the specified commit.

-   .. code-block:: shell
+   .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml

-      docker build -f docker/Dockerfile.rocm -t vllm-rocm .
+      {% set docker = data.dockers[0] %}
+      .. code-block:: shell
+
+         docker build -f docker/Dockerfile.rocm \
+             --build-arg REMOTE_VLLM=1 \
+             --build-arg VLLM_REPO=https://github.com/ROCm/vllm \
+             --build-arg VLLM_BRANCH="{{ docker.dockerfile.commit }}" \
+             -t vllm-rocm .
+
+   .. tip::
+
+      Replace ``vllm-rocm`` with your desired image tag.

 Further reading
 ===============
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
@@ -25,7 +25,7 @@ It includes the following software components:
      {% for docker in dockers %}
      {% set jax_version = docker.components["JAX"] %}

-      .. tab-item:: JAX {{ jax_version }}
+      .. tab-item:: ``{{ docker.pull_tag }}``
         :sync: {{ docker.pull_tag }}

         .. list-table::
@@ -132,6 +132,28 @@ This Docker image is optimized for specific model configurations outlined
 as follows. Performance can vary for other training workloads, as AMD
 doesn’t validate configurations and run conditions outside those described.

+Pull the Docker image
+---------------------
+
+Use the following command to pull the Docker image from Docker Hub.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+      {% for docker in dockers %}
+      {% set jax_version = docker.components["JAX"] %}
+
+      .. tab-item:: JAX {{ jax_version }}
+         :sync: {{ docker.pull_tag }}
+
+         .. code-block:: shell
+
+            docker pull {{ docker.pull_tag }}
+
+      {% endfor %}
+
 .. _amd-maxtext-multi-node-setup-v257:

 Multi-node configuration
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
@@ -105,21 +105,26 @@ system's configuration.

 .. _mi300x-amd-primus-megatron-lm-training:

+Environment setup
+=================
+
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml

   {% set dockers = data.dockers %}
      {% set docker = dockers[0] %}

-   Environment setup
-   =================
-
   Use the following instructions to set up the environment, configure the script to train models, and
   reproduce the benchmark results on MI300X series GPUs with the ``{{ docker.pull_tag }}`` image.

   .. _amd-primus-megatron-lm-requirements:

-   Download the Docker image
-   -------------------------
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+      {% set docker = dockers[0] %}

   1. Use the following command to pull the Docker image from Docker Hub.

--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
@@ -104,22 +104,25 @@ This Docker image is optimized for specific model configurations outlined
 below. Performance can vary for other training workloads, as AMD
 doesn’t test configurations and run conditions outside those described.

+Pull the Docker image
+=====================
+
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml

   {% set unified_docker = data.dockers[0] %}

-   Pull the Docker image
-   =====================
-
   Use the following command to pull the `Docker image <{{ unified_docker.docker_hub_url }}>`_ from Docker Hub.

   .. code-block:: shell

      docker pull {{ unified_docker.pull_tag }}

-   Run training
-   ============
+Run training
+============

+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
   {% set model_groups = data.model_groups %}

   Once the setup is complete, choose between the following two workflows to start benchmarking training.
--- a/docs/sphinx/requirements.in
+++ b/docs/sphinx/requirements.in
@@ -1,4 +1,4 @@
-rocm-docs-core==1.20.1
+rocm-docs-core==1.26.0
 sphinx-reredirects
 sphinx-sitemap
 sphinxcontrib.datatemplates==0.11.0
--- a/docs/sphinx/requirements.txt
+++ b/docs/sphinx/requirements.txt
@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile requirements.in
+#    pip-compile docs/sphinx/requirements.in
 #
 accessible-pygments==0.0.5
    # via pydata-sphinx-theme
@@ -10,7 +10,7 @@ alabaster==1.0.0
    # via sphinx
 asttokens==3.0.0
    # via stack-data
-attrs==25.3.0
+attrs==25.4.0
    # via
    #   jsonschema
    #   jupyter-cache
@@ -19,34 +19,32 @@ babel==2.17.0
    # via
    #   pydata-sphinx-theme
    #   sphinx
-beautifulsoup4==4.13.4
+beautifulsoup4==4.14.2
    # via pydata-sphinx-theme
 breathe==4.36.0
    # via rocm-docs-core
-certifi==2025.4.26
+certifi==2025.10.5
    # via requests
-cffi==1.17.1
+cffi==2.0.0
    # via
    #   cryptography
    #   pynacl
-charset-normalizer==3.4.2
+charset-normalizer==3.4.3
    # via requests
-click==8.2.1
+click==8.3.0
    # via
    #   jupyter-cache
    #   sphinx-external-toc
-comm==0.2.2
+comm==0.2.3
    # via ipykernel
-cryptography==45.0.3
+cryptography==46.0.2
    # via pyjwt
-debugpy==1.8.14
+debugpy==1.8.17
    # via ipykernel
 decorator==5.2.1
    # via ipython
 defusedxml==0.7.1
    # via sphinxcontrib-datatemplates
-deprecated==1.2.18
-    # via pygithub
 docutils==0.21.2
    # via
    #   myst-parser
@@ -54,17 +52,17 @@ docutils==0.21.2
    #   sphinx
 exceptiongroup==1.3.0
    # via ipython
-executing==2.2.0
+executing==2.2.1
    # via stack-data
-fastjsonschema==2.21.1
+fastjsonschema==2.21.2
    # via
    #   nbformat
    #   rocm-docs-core
 gitdb==4.0.12
    # via gitpython
-gitpython==3.1.44
+gitpython==3.1.45
    # via rocm-docs-core
-greenlet==3.2.3
+greenlet==3.2.4
    # via sqlalchemy
 idna==3.10
    # via requests
@@ -74,7 +72,7 @@ importlib-metadata==8.7.0
    # via
    #   jupyter-cache
    #   myst-nb
-ipykernel==6.29.5
+ipykernel==6.30.1
    # via myst-nb
 ipython==8.37.0
    # via
@@ -86,9 +84,9 @@ jinja2==3.1.6
    # via
    #   myst-parser
    #   sphinx
-jsonschema==4.24.0
+jsonschema==4.25.1
    # via nbformat
-jsonschema-specifications==2025.4.1
+jsonschema-specifications==2025.9.1
    # via jsonschema
 jupyter-cache==1.0.1
    # via myst-nb
@@ -106,17 +104,17 @@ markdown-it-py==3.0.0
    # via
    #   mdit-py-plugins
    #   myst-parser
-markupsafe==3.0.2
+markupsafe==3.0.3
    # via jinja2
 matplotlib-inline==0.1.7
    # via
    #   ipykernel
    #   ipython
-mdit-py-plugins==0.4.2
+mdit-py-plugins==0.5.0
    # via myst-parser
 mdurl==0.1.2
    # via markdown-it-py
-myst-nb==1.2.0
+myst-nb==1.3.0
    # via rocm-docs-core
 myst-parser==4.0.1
    # via myst-nb
@@ -134,31 +132,30 @@ nest-asyncio==1.6.0
 packaging==25.0
    # via
    #   ipykernel
-    #   pydata-sphinx-theme
    #   sphinx
-parso==0.8.4
+parso==0.8.5
    # via jedi
 pexpect==4.9.0
    # via ipython
-platformdirs==4.3.8
+platformdirs==4.4.0
    # via jupyter-core
-prompt-toolkit==3.0.51
+prompt-toolkit==3.0.52
    # via ipython
-psutil==7.0.0
+psutil==7.1.0
    # via ipykernel
 ptyprocess==0.7.0
    # via pexpect
 pure-eval==0.2.3
    # via stack-data
-pycparser==2.22
+pycparser==2.23
    # via cffi
-pydata-sphinx-theme==0.15.4
+pydata-sphinx-theme==0.16.1
    # via
    #   rocm-docs-core
    #   sphinx-book-theme
-pygithub==2.6.1
+pygithub==2.8.1
    # via rocm-docs-core
-pygments==2.19.1
+pygments==2.19.2
    # via
    #   accessible-pygments
    #   ipython
@@ -166,11 +163,11 @@ pygments==2.19.1
    #   sphinx
 pyjwt[crypto]==2.10.1
    # via pygithub
-pynacl==1.5.0
+pynacl==1.6.0
    # via pygithub
 python-dateutil==2.9.0.post0
    # via jupyter-client
-pyyaml==6.0.2
+pyyaml==6.0.3
    # via
    #   jupyter-cache
    #   myst-nb
@@ -178,7 +175,7 @@ pyyaml==6.0.2
    #   rocm-docs-core
    #   sphinx-external-toc
    #   sphinxcontrib-datatemplates
-pyzmq==26.4.0
+pyzmq==27.1.0
    # via
    #   ipykernel
    #   jupyter-client
@@ -186,13 +183,13 @@ referencing==0.36.2
    # via
    #   jsonschema
    #   jsonschema-specifications
-requests==2.32.4
+requests==2.32.5
    # via
    #   pygithub
    #   sphinx
-rocm-docs-core==1.20.1
-    # via -r requirements.in
-rpds-py==0.25.1
+rocm-docs-core==1.26.0
+    # via -r docs/sphinx/requirements.in
+rpds-py==0.27.1
    # via
    #   jsonschema
    #   referencing
@@ -202,7 +199,7 @@ smmap==5.0.2
    # via gitdb
 snowballstemmer==3.0.1
    # via sphinx
-soupsieve==2.7
+soupsieve==2.8
    # via beautifulsoup4
 sphinx==8.1.3
    # via
@@ -220,7 +217,7 @@ sphinx==8.1.3
    #   sphinx-reredirects
    #   sphinxcontrib-datatemplates
    #   sphinxcontrib-runcmd
-sphinx-book-theme==1.1.4
+sphinx-book-theme==1.1.3
    # via rocm-docs-core
 sphinx-copybutton==0.5.2
    # via rocm-docs-core
@@ -233,13 +230,13 @@ sphinx-last-updated-by-git==0.3.8
 sphinx-notfound-page==1.1.0
    # via rocm-docs-core
 sphinx-reredirects==0.1.6
-    # via -r requirements.in
-sphinx-sitemap==2.8.0
-    # via -r requirements.in
+    # via -r docs/sphinx/requirements.in
+sphinx-sitemap==2.9.0
+    # via -r docs/sphinx/requirements.in
 sphinxcontrib-applehelp==2.0.0
    # via sphinx
 sphinxcontrib-datatemplates==0.11.0
-    # via -r requirements.in
+    # via -r docs/sphinx/requirements.in
 sphinxcontrib-devhelp==2.0.0
    # via sphinx
 sphinxcontrib-htmlhelp==2.1.0
@@ -252,7 +249,7 @@ sphinxcontrib-runcmd==0.2.0
    # via sphinxcontrib-datatemplates
 sphinxcontrib-serializinghtml==2.0.0
    # via sphinx
-sqlalchemy==2.0.41
+sqlalchemy==2.0.43
    # via jupyter-cache
 stack-data==0.6.3
    # via ipython
@@ -260,13 +257,12 @@ tabulate==0.9.0
    # via jupyter-cache
 tomli==2.2.1
    # via sphinx
-tornado==6.5.1
+tornado==6.5.2
    # via
    #   ipykernel
    #   jupyter-client
 traitlets==5.14.3
    # via
-    #   comm
    #   ipykernel
    #   ipython
    #   jupyter-client
@@ -274,9 +270,10 @@ traitlets==5.14.3
    #   matplotlib-inline
    #   nbclient
    #   nbformat
-typing-extensions==4.14.0
+typing-extensions==4.15.0
    # via
    #   beautifulsoup4
+    #   cryptography
    #   exceptiongroup
    #   ipython
    #   myst-nb
@@ -288,9 +285,7 @@ urllib3==2.5.0
    # via
    #   pygithub
    #   requests
-wcwidth==0.2.13
+wcwidth==0.2.14
    # via prompt-toolkit
-wrapt==1.17.2
-    # via deprecated
 zipp==3.23.0
    # via importlib-metadata
--- a/tools/rocm-build/rocm-7.0.2.xml
+++ b/tools/rocm-build/rocm-7.0.2.xml
@@ -0,0 +1,68 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <default revision="refs/tags/rocm-7.0.2"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="ROCm" revision="roc-7.0.x" />
+    <project name="ROCK-Kernel-Driver" />
+    <project name="ROCR-Runtime" />
+    <project name="amdsmi" />
+    <project name="aqlprofile" />
+    <project name="rdc" />
+    <project name="rocm_bandwidth_test" />
+    <project name="rocm_smi_lib" />
+    <project name="rocm-core" />
+    <project name="rocm-examples" />
+    <project name="rocminfo" />
+    <project name="rocprofiler" />
+    <project name="rocprofiler-register" />
+    <project name="rocprofiler-sdk" />
+    <project name="rocprofiler-compute" />
+    <project name="rocprofiler-systems" />
+    <project name="roctracer" />
+<!--HIP Projects-->
+    <project name="hip" />
+    <project name="hip-tests" />
+    <project name="HIPIFY" />
+    <project name="clr" />
+    <project name="hipother" />
+<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
+    <project name="half" />
+    <project name="llvm-project" />
+    <project name="spirv-llvm-translator" />
+<!-- gdb projects -->
+    <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
+    <project name="rocr_debug_agent" />
+<!-- ROCm Libraries -->
+    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="MIVisionX" />
+    <project groups="mathlibs" name="ROCmValidationSuite" />
+    <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipTensor" />
+    <project groups="mathlibs" name="hipfort" />
+    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <!-- The following components have been migrated to rocm-libraries:
+        hipBLAS-common hipBLAS hipBLASLt hipCUB
+        hipFFT hipRAND hipSPARSE hipSPARSELt
+        MIOpen rocBLAS rocFFT rocPRIM rocRAND
+        rocSPARSE rocThrust Tensile -->
+    <project groups="mathlibs" name="rocm-libraries" />
+    <project groups="mathlibs" name="rocPyDecode" />
+    <project groups="mathlibs" name="rocSHMEM" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>
Author	SHA1	Message	Date
srayasam-amd	6be77f1fff	Create rocm-7.0.2.xml	2025-10-10 11:59:08 +05:30
srayasam-amd	9999c3c3c9	7.0.2 GA update	2025-10-10 11:57:38 +05:30
peterjunpark	68e8453ca5	Update vLLM doc for 10/6 release and bump rocm-docs-core to 1.26.0 (#5481 ) * archive previous doc version * update model/docker data and doc templates * Update "Reproducing the Docker image" * fix: truncated commit hash doesn't work for some reason * bump rocm-docs-core to 1.26.0 * fix numbering fix * update docker tag * update .wordlist.txt	2025-10-08 16:23:40 -04:00
Pratik Basyal	503b8bcc86	Framework and changelog updated (#5483 ) * Framework and chaneglog updated * Wordlist updated	2025-10-08 15:05:11 -04:00
amd-hsivasun	e3d97d339a	[Ex CI] Added rocJPEG and rocprofiler-sdk	2025-10-08 14:47:44 -04:00
amd-hsivasun	f20edab8fc	[Ex CI] Update CMake Flags for hipTensor	2025-10-07 15:21:39 -04:00
peterjunpark	eeea0d2180	Fix heading levels in pages using embedded templates (#5468 )	2025-10-03 13:33:14 -04:00