github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-02-12 07:25:22 -05:00
Code Issues Packages Projects Releases Wiki Activity

Update docs for xDiT diffusion inference 26.1 (#5955)

Browse Source 
* archive previous version

* xDiT diffusion inference docker 26.1
This commit is contained in:
peterjunpark
2026-02-11 13:27:36 -05:00
committed by GitHub
parent 19891f8ef1
commit fe8dff691d
6 changed files with 795 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files

105
docs/data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.13-inference-models.yaml Normal file
View File

@@ -0,0 +1,105 @@
docker:
pull_tag: rocm/pytorch-xdit:v25.13
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.13/images/sha256-81954713070d67bde08595e03f62110c8a3dd66a9ae17a77d611e01f83f0f4ef
ROCm: 7.11.0
whats_new:
- "Flux.1 Kontext support"
- "Flux.2 Dev support"
- "Flux FP8 GEMM support"
- "Hybrid FP8 attention support for Wan models"
components:
TheRock:
version: 1728a81
url: https://github.com/ROCm/TheRock
rccl:
version: d23d18f
url: https://github.com/ROCm/rccl
composable_kernel:
version: ab0101c
url: https://github.com/ROCm/composable_kernel
rocm-libraries:
version: a2f7c35
url: https://github.com/ROCm/rocm-libraries
rocm-systems:
version: 659737c
url: https://github.com/ROCm/rocm-systems
torch:
version: 91be249
url: https://github.com/ROCm/pytorch
torchvision:
version: b919bd0
url: https://github.com/pytorch/vision
triton:
version: a272dfa
url: https://github.com/ROCm/triton
accelerate:
version: b521400f
url: https://github.com/huggingface/accelerate
aiter:
version: de14bec0
url: https://github.com/ROCm/aiter
diffusers:
version: a1f36ee3e
url: https://github.com/huggingface/diffusers
xfuser:
version: adf2681
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
- model: FLUX.1 Kontext
model_repo: black-forest-labs/FLUX.1-Kontext-dev
url: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
github: https://github.com/black-forest-labs/flux
mad_tag: pyt_xdit_flux_kontext
js_tag: flux_1_kontext_tag
- model: FLUX.2
model_repo: black-forest-labs/FLUX.2-dev
url: https://huggingface.co/black-forest-labs/FLUX.2-dev
github: https://github.com/black-forest-labs/flux2
mad_tag: pyt_xdit_flux_2
js_tag: flux_2_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

196
docs/data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
View File

@@ -1,14 +1,13 @@
docker:
pull_tag: rocm/pytorch-xdit:v25.13
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.13/images/sha256-81954713070d67bde08595e03f62110c8a3dd66a9ae17a77d611e01f83f0f4ef
pull_tag: rocm/pytorch-xdit:v26.1
docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
ROCm: 7.11.0
whats_new:
- "Flux.1 Kontext support"
- "Flux.2 Dev support"
- "Flux FP8 GEMM support"
- "Hybrid FP8 attention support for Wan models"
- "HunyuanVideo 1.5 support"
- "Z-Image Turbo support"
- "Wan model sharding"
components:
TheRock:
TheRock:
version: 1728a81
url: https://github.com/ROCm/TheRock
rccl:
@@ -39,10 +38,10 @@ docker:
version: de14bec0
url: https://github.com/ROCm/aiter
diffusers:
version: a1f36ee3e
version: 6708f5
url: https://github.com/huggingface/diffusers
xfuser:
version: adf2681
version: 0a3d7a
url: https://github.com/xdit-project/xDiT
yunchang:
version: 2c9b712
@@ -58,6 +57,49 @@ docker:
github: https://github.com/Tencent-Hunyuan/HunyuanVideo
mad_tag: pyt_xdit_hunyuanvideo
js_tag: hunyuan_tag
benchmark_command:
- cd /app/Hunyuanvideo
- mkdir results
- 'torchrun --nproc_per_node=8 run.py \'
- '--model {model_repo} \'
- '--prompt "In the large cage, two puppies were wagging their tails at each other." \'
- '--batch_size 1 \'
- '--height 720 --width 1280 \'
- '--seed 1168860793 \'
- '--num_frames 129 \'
- '--num_inference_steps 50 \'
- '--warmup_steps 1 \'
- '--n_repeats 1 \'
- '--sleep_dur 10 \'
- '--ulysses_degree 8 \'
- '--enable_tiling --enable_slicing \'
- '--guidance_scale 6.0 \'
- '--use_torch_compile \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- model: Hunyuan Video 1.5
model_repo: hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v
url: https://huggingface.co/hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v
github: https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5
mad_tag: pyt_xdit_hunyuanvideo_1_5
js_tag: hunyuan_1_5_tag
benchmark_command:
- cd /app/Hunyuanvideo_1_5
- mkdir results
- 'torchrun --nproc_per_node=8 /app/Hunyuanvideo_1_5/run.py \'
- '--model {model_repo} \'
- '--prompt "In the large cage, two puppies were wagging their tails at each other." \'
- '--task t2v \'
- '--height 720 --width 1280 \'
- '--seed 1168860793 \'
- '--num_frames 129 \'
- '--num_inference_steps 50 \'
- '--num_repetitions 1 \'
- '--ulysses_degree 8 \'
- '--enable_tiling --enable_slicing \'
- '--use_torch_compile \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- group: Wan-AI
js_tag: wan
models:
@@ -67,12 +109,48 @@ docker:
github: https://github.com/Wan-Video/Wan2.1
mad_tag: pyt_xdit_wan_2_1
js_tag: wan_21_tag
benchmark_command:
- cd /app/Wan
- mkdir results
- 'torchrun --nproc_per_node=8 /app/Wan/run.py \'
- '--model {model_repo} \'
- '--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." \'
- '--task i2v \'
- '--height 720 \'
- '--width 1280 \'
- '--img_file_path /app/Wan/i2v_input.JPG \'
- '--num_frames 81 \'
- '--ulysses_degree 8 \'
- '--seed 42 \'
- '--num_repetitions 1 \'
- '--num_inference_steps 40 \'
- '--use_torch_compile \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- 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
benchmark_command:
- cd /app/Wan
- mkdir results
- 'torchrun --nproc_per_node=8 /app/Wan/run.py \'
- '--model {model_repo} \'
- '--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." \'
- '--task i2v \'
- '--height 720 \'
- '--width 1280 \'
- '--img_file_path /app/Wan/i2v_input.JPG \'
- '--num_frames 81 \'
- '--ulysses_degree 8 \'
- '--seed 42 \'
- '--num_repetitions 1 \'
- '--num_inference_steps 40 \'
- '--use_torch_compile \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- group: FLUX
js_tag: flux
models:
@@ -82,18 +160,79 @@ docker:
github: https://github.com/black-forest-labs/flux
mad_tag: pyt_xdit_flux
js_tag: flux_1_tag
benchmark_command:
- cd /app/Flux
- mkdir results
- 'torchrun --nproc_per_node=8 /app/Flux/run.py \'
- '--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 \'
- '--guidance_scale 0.0 \'
- '--num_repetitions 50 \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- model: FLUX.1 Kontext
model_repo: black-forest-labs/FLUX.1-Kontext-dev
url: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
github: https://github.com/black-forest-labs/flux
mad_tag: pyt_xdit_flux_kontext
js_tag: flux_1_kontext_tag
benchmark_command:
- cd /app/Flux
- mkdir results
- 'torchrun --nproc_per_node=8 /app/Flux/run_usp.py \'
- '--model {model_repo} \'
- '--seed 42 \'
- '--prompt "Add a cool hat to the cat" \'
- '--height 1024 \'
- '--width 1024 \'
- '--num_inference_steps 30 \'
- '--max_sequence_length 512 \'
- '--warmup_steps 5 \'
- '--no_use_resolution_binning \'
- '--ulysses_degree 8 \'
- '--use_torch_compile \'
- '--img_file_path /app/Flux/cat.png \'
- '--model_type flux_kontext \'
- '--guidance_scale 2.5 \'
- '--num_repetitions 25 \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- model: FLUX.2
model_repo: black-forest-labs/FLUX.2-dev
url: https://huggingface.co/black-forest-labs/FLUX.2-dev
github: https://github.com/black-forest-labs/flux2
mad_tag: pyt_xdit_flux_2
js_tag: flux_2_tag
benchmark_command:
- cd /app/Flux
- mkdir results
- 'torchrun --nproc_per_node=8 /app/Flux/run_usp.py \'
- '--model {model_repo} \'
- '--seed 42 \'
- '--prompt "Add a cool hat to the cat" \'
- '--height 1024 \'
- '--width 1024 \'
- '--num_inference_steps 50 \'
- '--max_sequence_length 512 \'
- '--warmup_steps 5 \'
- '--no_use_resolution_binning \'
- '--ulysses_degree 8 \'
- '--use_torch_compile \'
- '--img_file_paths /app/Flux/cat.png \'
- '--model_type flux2 \'
- '--guidance_scale 4.0 \'
- '--num_repetitions 25 \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- group: StableDiffusion
js_tag: stablediffusion
models:
@@ -103,3 +242,42 @@ docker:
github: https://github.com/Stability-AI/sd3.5
mad_tag: pyt_xdit_sd_3_5
js_tag: stable_diffusion_3_5_large_tag
benchmark_command:
- cd /app/StableDiffusion3.5
- mkdir results
- 'torchrun --nproc_per_node=8 /app/StableDiffusion3.5/run.py \'
- '--model {model_repo} \'
- '--prompt "A capybara holding a sign that reads Hello World" \'
- '--num_repetitions 50 \'
- '--num_inference_steps 28 \'
- '--pipefusion_parallel_degree 4 \'
- '--use_cfg_parallel \'
- '--use_torch_compile \'
- '--dtype torch.float16 \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'
- group: Z-Image
js_tag: z_image
models:
- model: Z-Image Turbo
model_repo: Tongyi-MAI/Z-Image-Turbo
url: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
github: https://github.com/Tongyi-MAI/Z-Image
mad_tag: pyt_xdit_z_image_turbo
js_tag: z_image_turbo_tag
benchmark_command:
- cd /app/Z-Image
- mkdir results
- 'torchrun --nproc_per_node=2 /app/Z-Image/run.py \'
- '--model {model_repo} \'
- '--seed 42 \'
- '--prompt "A crowded beach" \'
- '--height 1088 \'
- '--width 1920 \'
- '--num_inference_steps 9 \'
- '--ulysses_degree 2 \'
- '--use_torch_compile \'
- '--guidance_scale 0.0 \'
- '--num_repetitions 50 \'
- '--attention_backend aiter \'
- '--benchmark_output_directory results'

6
docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.12.rst
View File

@@ -11,7 +11,7 @@ xDiT diffusion inference
.. caution::
This documentation does not reflect the latest version of ROCm vLLM
This documentation does not reflect the latest version of xDiT diffusion
inference performance documentation. See
:doc:`/how-to/rocm-for-ai/inference/xdit-diffusion-inference` for the latest
version.
@@ -293,7 +293,7 @@ Run inference
--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``
@@ -379,7 +379,7 @@ Run inference
{% endif %}
{% if model.model == "stable-diffusion-3.5-large" %}
cd StableDiffusion3.5
cd StableDiffusion3.5
mkdir results
torchrun --nproc_per_node=8 /app/StableDiffusion3.5/run.py \

474
docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.13.rst Normal file
View File

@@ -0,0 +1,474 @@
:orphan:
.. 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
************************
.. caution::
This documentation does not reflect the latest version of the xDiT diffusion
inference performance documentation. See
:doc:`/how-to/rocm-for-ai/inference/xdit-diffusion-inference` for the latest
version.
.. _xdit-video-diffusion-2513:
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.13-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 AMD Instinct MI355X, MI350X (gfx950), MI325X,
and MI300X (gfx942) GPUs.
The image runs a preview version of ROCm using the new `TheRock
<https://github.com/ROCm/TheRock>`__ build system and includes the following
components:
.. dropdown:: Software components - {{ docker.pull_tag.split('-')|last }}
.. 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/previous-versions/xdit_25.13-inference-models.yaml
{% set docker = data.docker %}
{% for item in docker.whats_new %}
* {{ item }}
{% endfor %}
.. _xdit-video-diffusion-supported-models-2513:
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/previous-versions/xdit_25.13-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 %}
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#tabs-a8543b7e6d-item-9eda09e707-tab>`__
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#tabs-a8543b7e6d-item-9eda09e707-tab>`__
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 GPUs 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.
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/previous-versions/xdit_25.13-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/previous-versions/xdit_25.13-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-2513` 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/previous-versions/xdit_25.13-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/previous-versions/xdit_25.13-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 /app/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 /app/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 /app/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 == "FLUX.1 Kontext" %}
cd /app/Flux
mkdir results
torchrun --nproc_per_node=8 /app/Flux/run_usp.py \
--model {{ model.model_repo }} \
--seed 42 \
--prompt "Add a cool hat to the cat" \
--height 1024 \
--width 1024 \
--num_inference_steps 30 \
--max_sequence_length 512 \
--warmup_steps 5 \
--no_use_resolution_binning \
--ulysses_degree 8 \
--use_torch_compile \
--img_file_path /app/Flux/cat.png \
--model_type flux_kontext \
--guidance_scale 2.5 \
--num_repetitions 25
{% endif %}
{% if model.model == "FLUX.2" %}
cd /app/Flux
mkdir results
torchrun --nproc_per_node=8 /app/Flux/run_usp.py \
--model {{ model.model_repo }} \
--seed 42 \
--prompt "Add a cool hat to the cat" \
--height 1024 \
--width 1024 \
--num_inference_steps 50 \
--max_sequence_length 512 \
--warmup_steps 5 \
--no_use_resolution_binning \
--ulysses_degree 8 \
--use_torch_compile \
--img_file_paths /app/Flux/cat.png \
--model_type flux2 \
--guidance_scale 4.0 \
--num_repetitions 25
{% endif %}
{% if model.model == "stable-diffusion-3.5-large" %}
cd /app/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 in ["FLUX.1", "FLUX.1 Kontext", "FLUX.2"] %}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 %}
Previous versions
=================
See
:doc:`/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history`
to find documentation for previous releases of xDiT diffusion inference
performance testing.

25
docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history.rst
View File

@@ -15,33 +15,40 @@ benchmarking, see the version-specific documentation.
- Components
- Resources
* - ``rocm/pytorch-xdit:v25.13`` (latest)
-
* - ``rocm/pytorch-xdit:v26.1``
-
* TheRock 1728a81
-
-
* :doc:`Documentation <../../xdit-diffusion-inference>`
* `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v26.1/images/sha256-4e35ebcad47042a41389b992ecb3489b3b0a922e4c34c7a0dd1098733a3db513>`__
* - ``rocm/pytorch-xdit:v25.13``
-
* TheRock 1728a81
-
* :doc:`Documentation <xdit-25.13>`
* `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v25.13/images/sha256-81954713070d67bde08595e03f62110c8a3dd66a9ae17a77d611e01f83f0f4ef>`__
* - ``rocm/pytorch-xdit:v25.12``
-
-
* `ROCm 7.10.0 preview <https://rocm.docs.amd.com/en/7.10.0-preview/about/release-notes.html>`__
* TheRock 3e3f834
-
-
* :doc:`Documentation <xdit-25.12>`
* `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v25.12/images/sha256-e06895132316bf3c393366b70a91eaab6755902dad0100e6e2b38310547d9256>`__
* - ``rocm/pytorch-xdit:v25.11``
-
-
* `ROCm 7.10.0 preview <https://rocm.docs.amd.com/en/7.10.0-preview/about/release-notes.html>`__
* TheRock 3e3f834
-
-
* :doc:`Documentation <xdit-25.11>`
* `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v25.11/images/sha256-c9fa659439bb024f854b4d5eea598347251b02c341c55f66c98110832bde4216>`__
* - ``rocm/pytorch-xdit:v25.10``
-
-
* `ROCm 7.9.0 preview <https://rocm.docs.amd.com/en/7.9.0-preview/about/release-notes.html>`__
* TheRock 7afbe45
-
-
* :doc:`Documentation <xdit-25.10>`
* `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v25.10/images/sha256-d79715ff18a9470e3f907cec8a9654d6b783c63370b091446acffc0de4d7070e>`__

178
docs/how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
View File

@@ -13,15 +13,10 @@ xDiT diffusion inference
{% 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 AMD Instinct MI355X, MI350X (gfx950), MI325X,
and MI300X (gfx942) GPUs.
The image runs a preview version of ROCm using the new `TheRock
<https://github.com/ROCm/TheRock>`__ build system and includes the following
components:
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 - {{ docker.pull_tag.split('-')|last }}
@@ -105,22 +100,6 @@ vary by model -- select one to get started.
{% endfor %}
{% endfor %}
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#tabs-a8543b7e6d-item-9eda09e707-tab>`__
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#tabs-a8543b7e6d-item-9eda09e707-tab>`__
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 GPUs or ROCm software.
System validation
=================
@@ -300,7 +279,7 @@ Run inference
--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``
@@ -311,152 +290,15 @@ Run inference
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
{{ model.benchmark_command
| map('replace', '{model_repo}', model.model_repo)
| map('trim')
| join('\n ') }}
{% endif %}
{% if model.model == "Wan2.1" %}
cd /app/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 /app/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 /app/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 == "FLUX.1 Kontext" %}
cd /app/Flux
mkdir results
torchrun --nproc_per_node=8 /app/Flux/run_usp.py \
--model {{ model.model_repo }} \
--seed 42 \
--prompt "Add a cool hat to the cat" \
--height 1024 \
--width 1024 \
--num_inference_steps 30 \
--max_sequence_length 512 \
--warmup_steps 5 \
--no_use_resolution_binning \
--ulysses_degree 8 \
--use_torch_compile \
--img_file_path /app/Flux/cat.png \
--model_type flux_kontext \
--guidance_scale 2.5 \
--num_repetitions 25
{% endif %}
{% if model.model == "FLUX.2" %}
cd /app/Flux
mkdir results
torchrun --nproc_per_node=8 /app/Flux/run_usp.py \
--model {{ model.model_repo }} \
--seed 42 \
--prompt "Add a cool hat to the cat" \
--height 1024 \
--width 1024 \
--num_inference_steps 50 \
--max_sequence_length 512 \
--warmup_steps 5 \
--no_use_resolution_binning \
--ulysses_degree 8 \
--use_torch_compile \
--img_file_paths /app/Flux/cat.png \
--model_type flux2 \
--guidance_scale 4.0 \
--num_repetitions 25
{% endif %}
{% if model.model == "stable-diffusion-3.5-large" %}
cd /app/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 in ["FLUX.1", "FLUX.1 Kontext", "FLUX.2"] %}results/timing.json{% elif model.model == "stable-diffusion-3.5-large"%}benchmark_results.csv{% endif %}
The generated video will be stored under the results directory.
{% if model.model == "FLUX.1" %}You may also use ``run_usp.py`` which implements USP without modifying the default diffusers pipeline. {% endif %}
{% endfor %}
{% endfor %}
Previous versions
=================
See :doc:`benchmark-docker/previous-versions/xdit-history` to find documentation for previous releases
of xDiT diffusion inference performance testing.