Merge branch 'develop' into docs/xdit-diffusion-v25-12

Co-authored-by: Pratik Basyal <prbasyal@amd.com>

.wordlist.txt

@@ -36,6 +36,7 @@ Andrej
 Arb
 Autocast
 autograd
+Backported
 BARs
 BatchNorm
 BLAS
@@ -138,6 +139,7 @@ ESXi
 EP
 EoS
 etcd
+equalto
 fas
 FBGEMM
 FiLM
@@ -202,9 +204,11 @@ GenAI
 GenZ
 GitHub
 Gitpod
+hardcoded
 HBM
 HCA
 HGX
+HLO
 HIPCC
 hipDataType
 HIPExtension
@@ -226,6 +230,8 @@ href
 Hyperparameters
 HybridEngine
 Huggingface
+Hunyuan
+HunyuanVideo
 IB
 ICD
 ICT
@@ -258,6 +264,7 @@ Ioffe
 JAX's
 JAXLIB
 Jinja
+js
 JSON
 Jupyter
 KFD
@@ -329,6 +336,7 @@ MoEs
 Mooncake
 Mpops
 Multicore
+multihost
 Multithreaded
 mx
 MXFP
@@ -541,6 +549,7 @@ UAC
 UC
 UCC
 UCX
+ud
 UE
 UIF
 UMC
@@ -852,6 +861,7 @@ pallas
 parallelization
 parallelizing
 param
+params
 parameterization
 passthrough
 pe
@@ -898,6 +908,7 @@ querySelectorAll
 queueing
 qwen
 radeon
+rc
 rccl
 rdc
 rdma
@@ -959,6 +970,7 @@ scalability
 scalable
 scipy
 seealso
+selectattr
 selectedTag
 sendmsg
 seqs
@@ -1020,6 +1032,7 @@ uncacheable
 uncorrectable
 underoptimized
 unhandled
+unfused
 uninstallation
 unmapped
 unsqueeze
@@ -1062,6 +1075,8 @@ writebacks
 wrreq
 wzo
 xargs
+xdit
+xDiT
 xGMI
 xPacked
 xz

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

@@ -269,6 +269,33 @@ For a complete and up-to-date list of JAX public modules (for example, ``jax.num
   JAX API modules are maintained by the JAX project and is subject to change.
   Refer to the official Jax documentation for the most up-to-date information.
 
+Key features and enhancements for ROCm 7.1
+===============================================================================
+
+- Enabled compilation of multihost HLO runner Python bindings.
+
+  - Backported multihost HLO runner bindings and some related changes to
+    :code:`FunctionalHloRunner`.
+
+  - Added :code:`requirements_lock_3_12` to enable building for Python 3.12.
+
+- Removed hardcoded NHWC convolution layout for ``fp16`` precision to address the performance drops for ``fp16`` precision on gfx12xx GPUs.
+
+
+- ROCprofiler-SDK integration:
+
+  - Integrated ROCprofiler-SDK (v3) to XLA to improve profiling of GPU events,
+    support both time-based and step-based profiling.
+
+  - Added unit tests for :code:`rocm_collector` and :code:`rocm_tracer`.
+
+- Added Triton unsupported conversion from ``f8E4M3FNUZ`` to ``fp16`` with
+  rounding mode.
+
+- Introduced :code:`CudnnFusedConvDecomposer` to revert fused convolutions
+  when :code:`ConvAlgorithmPicker` fails to find a fused algorithm, and removed
+  unfused fallback paths from :code:`RocmFusedConvRunner`.
+
 Key features and enhancements for ROCm 7.0
 ===============================================================================
 

docs/conf.py

@@ -145,6 +145,7 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.4", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/xdit-diffusion-inference", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},

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

@@ -0,0 +1,91 @@
+docker:
+  pull_tag: rocm/pytorch-xdit:v25.12
+  docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
+  ROCm: 7.10.0
+  whats_new:
+      - "Adds T2V and TI2V support for Wan models."
+      - "Adds support for SD-3.5 T2I model."
+  components:
+    TheRock: 
+      version: 3e3f834
+      url: https://github.com/ROCm/TheRock
+    rccl:
+      version: d23d18f
+      url: https://github.com/ROCm/rccl
+    composable_kernel:
+      version: 2570462
+      url: https://github.com/ROCm/composable_kernel
+    rocm-libraries:
+      version: 0588f07
+      url: https://github.com/ROCm/rocm-libraries
+    rocm-systems:
+      version: 473025a
+      url: https://github.com/ROCm/rocm-systems
+    torch:
+      version: 73adac
+      url: https://github.com/pytorch/pytorch
+    torchvision:
+      version: f5c6c2e
+      url: https://github.com/pytorch/vision
+    triton:
+      version: 7416ffc
+      url: https://github.com/triton-lang/triton
+    accelerate:
+      version: 34c1779
+      url: https://github.com/huggingface/accelerate
+    aiter:
+      version: de14bec
+      url: https://github.com/ROCm/aiter
+    diffusers:
+      version: 40528e9
+      url: https://github.com/huggingface/diffusers
+    xfuser:
+      version: ccba9d5
+      url: https://github.com/xdit-project/xDiT
+    yunchang:
+      version: 2c9b712
+      url: https://github.com/feifeibear/long-context-attention
+  supported_models:
+    - group: Hunyuan Video
+      js_tag: hunyuan
+      models:
+        - model: Hunyuan Video
+          model_repo: tencent/HunyuanVideo
+          revision: refs/pr/18
+          url: https://huggingface.co/tencent/HunyuanVideo
+          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
+          mad_tag: pyt_xdit_hunyuanvideo
+          js_tag: hunyuan_tag
+    - group: Wan-AI
+      js_tag: wan
+      models:
+        - model: Wan2.1
+          model_repo: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          github: https://github.com/Wan-Video/Wan2.1
+          mad_tag: pyt_xdit_wan_2_1
+          js_tag: wan_21_tag
+        - model: Wan2.2
+          model_repo: Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          github: https://github.com/Wan-Video/Wan2.2
+          mad_tag: pyt_xdit_wan_2_2
+          js_tag: wan_22_tag
+    - group: FLUX
+      js_tag: flux
+      models:
+        - model: FLUX.1
+          model_repo: black-forest-labs/FLUX.1-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+          github: https://github.com/black-forest-labs/flux
+          mad_tag: pyt_xdit_flux
+          js_tag: flux_1_tag
+    - group: StableDiffusion
+      js_tag: stablediffusion
+      models:
+        - model: stable-diffusion-3.5-large
+          model_repo: stabilityai/stable-diffusion-3.5-large
+          url: https://huggingface.co/stabilityai/stable-diffusion-3.5-large
+          github: https://github.com/Stability-AI/sd3.5
+          mad_tag: pyt_xdit_sd_3_5
+          js_tag: stable_diffusion_3_5_large_tag

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

@@ -27,3 +27,5 @@ training, fine-tuning, and inference. It leverages popular machine learning fram
 - :doc:`SGLang inference performance testing <benchmark-docker/sglang>`
 
 - :doc:`Deploying your model <deploy-your-model>`
+
+- :doc:`xDiT diffusion inference <xdit-diffusion-inference>`

docs/how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst

@@ -0,0 +1,389 @@
+.. meta::
+   :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using
+                 prebuilt and optimized docker images.
+   :keywords: xDiT, diffusion, video, video generation, image, image generation, validate, benchmark
+
+************************
+xDiT diffusion inference
+************************
+
+.. _xdit-video-diffusion:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers a prebuilt, optimized environment based on `xDiT <https://github.com/xdit-project/xDiT>`_ for
+   benchmarking diffusion model video and image generation on gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X) GPUs.
+   The image runs ROCm **{{docker.ROCm}}** (preview) based on `TheRock <https://github.com/ROCm/TheRock>`_
+   and includes the following components:
+
+   .. dropdown:: Software components
+
+      .. list-table::
+         :header-rows: 1
+
+         * - Software component
+           - Version
+
+         {% for component_name, component_data in docker.components.items() %}
+         * - `{{ component_name }} <{{ component_data.url }}>`_
+           - {{ component_data.version }}
+         {% endfor %}
+
+Follow this guide to pull the required image, spin up a container, download the model, and run a benchmark.
+For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.docker.com/r/amdsiloai/pytorch-xdit>`_.
+
+What's new
+==========
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   {% for item in docker.whats_new %}
+   * {{ item }}
+   {% endfor %}
+
+.. _xdit-video-diffusion-supported-models:
+
+Supported models
+================
+
+The following models are supported for inference performance benchmarking.
+Some instructions, commands, and recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   .. 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 docker.supported_models %}
+               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.js_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 docker.supported_models %}
+            {% 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.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
+                {% else %}
+                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
+                {% endif %}
+            {% endfor %}
+        {% endfor %}
+              </div>
+          </div>
+      </div>
+
+   {% for model_group in docker.supported_models %}
+       {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.js_tag }}
+
+      .. note::
+
+         To learn more about your specific model see the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_
+         or visit the `GitHub page <{{ model.github }}>`__. Note that some models require access authorization before use via an
+         external license agreement through a third party.
+
+       {% endfor %}
+   {% endfor %}
+
+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.
+
+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.
+
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   For this tutorial, it's recommended to use the latest ``{{ docker.pull_tag }}`` Docker image.
+   Pull the image using the following command:
+
+   .. code-block:: shell
+
+      docker pull {{ docker.pull_tag }}
+
+Validate and benchmark
+======================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   Once the image has been downloaded you can follow these steps to
+   run benchmarks and generate outputs.
+
+   {% for model_group in docker.supported_models %}
+     {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.js_tag}}
+
+      The following commands are written for {{ model.model }}.
+      See :ref:`xdit-video-diffusion-supported-models` to switch to another available model.
+
+     {% endfor %}
+   {% endfor %}
+
+Choose your setup method
+------------------------
+
+You can either use an existing Hugging Face cache or download the model fresh inside the container.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   {% for model_group in docker.supported_models %}
+     {% for model in model_group.models %}
+   .. container:: model-doc {{model.js_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: Option 1: Use existing Hugging Face cache
+
+            If you already have models downloaded on your host system, you can mount your existing cache.
+
+            1. Set your Hugging Face cache location.
+
+               .. code-block:: shell
+
+                  export HF_HOME=/your/hf_cache/location
+
+            2. Download the model (if not already cached).
+
+               .. code-block:: shell
+
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+
+            3. Launch the container with mounted cache.
+
+               .. code-block:: shell
+
+                  docker run \
+                      -it --rm \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --user root \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --ipc=host \
+                      --network host \
+                      --privileged \
+                      --shm-size 128G \
+                      --name pytorch-xdit \
+                      -e HSA_NO_SCRATCH_RECLAIM=1 \
+                      -e OMP_NUM_THREADS=16 \
+                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+                      -e HF_HOME=/app/huggingface_models \
+                      -v $HF_HOME:/app/huggingface_models \
+                      {{ docker.pull_tag }}
+
+         .. tab-item:: Option 2: Download inside container
+
+            If you prefer to keep the container self-contained or don't have an existing cache.
+
+            1. Launch the container
+
+               .. code-block:: shell
+
+                  docker run \
+                      -it --rm \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --user root \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --ipc=host \
+                      --network host \
+                      --privileged \
+                      --shm-size 128G \
+                      --name pytorch-xdit \
+                      -e HSA_NO_SCRATCH_RECLAIM=1 \
+                      -e OMP_NUM_THREADS=16 \
+                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+                      {{ docker.pull_tag }}
+
+            2. Inside the container, set the Hugging Face cache location and download the model.
+
+               .. code-block:: shell
+
+                  export HF_HOME=/app/huggingface_models
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+
+               .. warning::
+
+                  Models will be downloaded to the container's filesystem and will be lost when the container is removed unless you persist the data with a volume.
+     {% endfor %}
+   {% endfor %}
+
+Run inference
+=============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.docker %}
+
+   {% for model_group in docker.supported_models %}
+     {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.js_tag }}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. On the host machine, use this command to run the performance benchmark test on
+               the `{{model.model}} <{{ model.url }}>`_ model using one node.
+
+               .. 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
+                     
+            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``.
+
+         .. tab-item:: Standalone benchmarking
+
+            To run the benchmarks for {{ model.model }}, use the following command:
+
+            .. code-block:: shell
+            {% if model.model == "Hunyuan Video" %}
+               cd /app/Hunyuanvideo
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --model {{ model.model_repo }} \
+                  --prompt "In the large cage, two puppies were wagging their tails at each other." \
+                  --height 720 --width 1280 --num_frames 129 \
+                  --num_inference_steps 50 --warmup_steps 1 --n_repeats 1 \
+                  --ulysses_degree 8 \
+                  --enable_tiling --enable_slicing \
+                  --use_torch_compile \
+                  --bench_output results
+
+            {% endif %}
+            {% if model.model == "Wan2.1" %}
+               cd Wan
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/Wan/run.py \
+                  --task i2v \
+                  --height 720 \
+                  --width 1280 \
+                  --model {{ model.model_repo }} \
+                  --img_file_path /app/Wan/i2v_input.JPG \
+                  --ulysses_degree 8 \
+                  --seed 42 \
+                  --num_frames 81 \
+                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
+                  --num_repetitions 1 \
+                  --num_inference_steps 40 \
+                  --use_torch_compile
+
+            {% endif %}
+            {% if model.model == "Wan2.2" %}
+               cd Wan
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/Wan/run.py \
+                  --task i2v \
+                  --height 720 \
+                  --width 1280 \
+                  --model {{ model.model_repo }} \
+                  --img_file_path /app/Wan/i2v_input.JPG \
+                  --ulysses_degree 8 \
+                  --seed 42 \
+                  --num_frames 81 \
+                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
+                  --num_repetitions 1 \
+                  --num_inference_steps 40 \
+                  --use_torch_compile
+
+            {% endif %}
+
+            {% if model.model == "FLUX.1" %}
+               cd Flux
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/Flux/run.py \
+                  --model {{ model.model_repo }} \
+                  --seed 42 \
+                  --prompt "A small cat" \
+                  --height 1024 \
+                  --width 1024 \
+                  --num_inference_steps 25 \
+                  --max_sequence_length 256 \
+                  --warmup_steps 5 \
+                  --no_use_resolution_binning \
+                  --ulysses_degree 8 \
+                  --use_torch_compile \
+                  --num_repetitions 50
+
+            {% endif %}
+
+            {% if model.model == "stable-diffusion-3.5-large" %}
+               cd StableDiffusion3.5 
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/StableDiffusion3.5/run.py \
+                  --model {{ model.model_repo }} \
+                  --num_inference_steps 28 \
+                  --prompt "A capybara holding a sign that reads Hello World" \
+                  --use_torch_compile \
+                  --pipefusion_parallel_degree 4 \
+                  --use_cfg_parallel \
+                  --num_repetitions 50 \
+                  --dtype torch.float16 \
+                  --output_path results
+
+            {% endif %}
+
+            The generated video will be stored under the results directory. For the actual benchmark step runtimes, see {% if model.model == "Hunyuan Video" %}stdout.{% elif model.model in ["Wan2.1", "Wan2.2"] %}results/outputs/rank0_*.json{% elif model.model == "FLUX.1" %}results/timing.json{% elif model.model == "stable-diffusion-3.5-large"%}benchmark_results.csv{% endif %}
+
+            {% if model.model == "FLUX.1" %}You may also use ``run_usp.py`` which implements USP without modifying the default diffusers pipeline. {% endif %}
+
+      {% endfor %}
+    {% endfor %}

docs/sphinx/_toc.yml.in

@@ -117,6 +117,8 @@ subtrees:
             title: SGLang inference performance testing
           - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
             title: SGLang distributed inference with Mooncake
+          - file: how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
+            title: xDiT diffusion inference
           - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
             title: Deploy your model