mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-06 21:33:57 -05:00
Update docs for xDiT diffusion inference 25.13 Docker release (#5820)
* archive previous version * add xdit 25.13 * update history index * add perf results section
This commit is contained in:
peterjunpark
@@ -194,6 +194,10 @@ article_pages = [
|
||||
{"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/sglang-history", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/xdit-diffusion-inference", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.10", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.11", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.12", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.13", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/inference/deploy-your-model", "os": ["linux"]},
|
||||
|
||||
{"file": "how-to/rocm-for-ai/inference-optimization/index", "os": ["linux"]},
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
xdit_diffusion_inference:
|
||||
docker:
|
||||
pull_tag: rocm/pytorch-xdit:v25.10
|
||||
docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.10/images/sha256-d79715ff18a9470e3f907cec8a9654d6b783c63370b091446acffc0de4d7070e
|
||||
ROCm: 7.9.0
|
||||
components:
|
||||
TheRock: 7afbe45
|
||||
|
||||
@@ -2,7 +2,7 @@ xdit_diffusion_inference:
|
||||
docker:
|
||||
- version: v25-11
|
||||
pull_tag: rocm/pytorch-xdit:v25.11
|
||||
docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.11/images/sha256-c9fa659439bb024f854b4d5eea598347251b02c341c55f66c98110832bde4216
|
||||
ROCm: 7.10.0
|
||||
supported_models:
|
||||
- group: Hunyuan Video
|
||||
|
||||
@@ -0,0 +1,91 @@
|
||||
docker:
|
||||
pull_tag: rocm/pytorch-xdit:v25.12
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.12/images/sha256-e06895132316bf3c393366b70a91eaab6755902dad0100e6e2b38310547d9256
|
||||
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: Stable Diffusion
|
||||
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
|
||||
@@ -1,46 +1,48 @@
|
||||
docker:
|
||||
pull_tag: rocm/pytorch-xdit:v25.12
|
||||
docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
|
||||
ROCm: 7.10.0
|
||||
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:
|
||||
- "Adds T2V and TI2V support for Wan models."
|
||||
- "Adds support for SD-3.5 T2I model."
|
||||
- "Flux.1 Kontext support"
|
||||
- "Flux.2 Dev support"
|
||||
- "Flux FP8 GEMM support"
|
||||
- "Hybrid FP8 attention support for Wan models"
|
||||
components:
|
||||
TheRock:
|
||||
version: 3e3f834
|
||||
version: 1728a81
|
||||
url: https://github.com/ROCm/TheRock
|
||||
rccl:
|
||||
version: d23d18f
|
||||
url: https://github.com/ROCm/rccl
|
||||
composable_kernel:
|
||||
version: 2570462
|
||||
version: ab0101c
|
||||
url: https://github.com/ROCm/composable_kernel
|
||||
rocm-libraries:
|
||||
version: 0588f07
|
||||
version: a2f7c35
|
||||
url: https://github.com/ROCm/rocm-libraries
|
||||
rocm-systems:
|
||||
version: 473025a
|
||||
version: 659737c
|
||||
url: https://github.com/ROCm/rocm-systems
|
||||
torch:
|
||||
version: 73adac
|
||||
url: https://github.com/pytorch/pytorch
|
||||
version: 91be249
|
||||
url: https://github.com/ROCm/pytorch
|
||||
torchvision:
|
||||
version: f5c6c2e
|
||||
version: b919bd0
|
||||
url: https://github.com/pytorch/vision
|
||||
triton:
|
||||
version: 7416ffc
|
||||
url: https://github.com/triton-lang/triton
|
||||
version: a272dfa
|
||||
url: https://github.com/ROCm/triton
|
||||
accelerate:
|
||||
version: 34c1779
|
||||
version: b521400f
|
||||
url: https://github.com/huggingface/accelerate
|
||||
aiter:
|
||||
version: de14bec
|
||||
version: de14bec0
|
||||
url: https://github.com/ROCm/aiter
|
||||
diffusers:
|
||||
version: 40528e9
|
||||
version: a1f36ee3e
|
||||
url: https://github.com/huggingface/diffusers
|
||||
xfuser:
|
||||
version: ccba9d5
|
||||
version: adf2681
|
||||
url: https://github.com/xdit-project/xDiT
|
||||
yunchang:
|
||||
version: 2c9b712
|
||||
@@ -80,7 +82,19 @@ docker:
|
||||
github: https://github.com/black-forest-labs/flux
|
||||
mad_tag: pyt_xdit_flux
|
||||
js_tag: flux_1_tag
|
||||
- group: Stable Diffusion
|
||||
- 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
|
||||
|
||||
@@ -0,0 +1,411 @@
|
||||
: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 ROCm vLLM
|
||||
inference performance documentation. See
|
||||
:doc:`/how-to/rocm-for-ai/inference/xdit-diffusion-inference` for the latest
|
||||
version.
|
||||
|
||||
.. _xdit-video-diffusion-2512:
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.12-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 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/previous-versions/xdit_25.12-inference-models.yaml
|
||||
|
||||
{% set docker = data.docker %}
|
||||
|
||||
{% for item in docker.whats_new %}
|
||||
* {{ item }}
|
||||
{% endfor %}
|
||||
|
||||
.. _xdit-video-diffusion-supported-models-2512:
|
||||
|
||||
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_25.12-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/previous-versions/xdit_25.12-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_25.12-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/previous-versions/xdit_25.12-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_25.12-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 %}
|
||||
|
||||
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.
|
||||
@@ -15,12 +15,20 @@ benchmarking, see the version-specific documentation.
|
||||
- Components
|
||||
- Resources
|
||||
|
||||
* - ``rocm/pytorch-xdit:v25.12`` (latest)
|
||||
* - ``rocm/pytorch-xdit:v25.13`` (latest)
|
||||
-
|
||||
* `ROCm 7.10.0 preview <https://rocm.docs.amd.com/en/7.10.0-preview/about/release-notes.html>`__
|
||||
* TheRock 1728a81
|
||||
-
|
||||
* :doc:`Documentation <../../xdit-diffusion-inference>`
|
||||
* `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-diffusion-inference>`
|
||||
* :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``
|
||||
|
||||
@@ -22,7 +22,7 @@ xDiT diffusion inference
|
||||
The image runs ROCm **{{docker.ROCm}}** (preview) based on `TheRock <https://github.com/ROCm/TheRock>`_
|
||||
and includes the following components:
|
||||
|
||||
.. dropdown:: Software components
|
||||
.. dropdown:: Software components - {{ docker.pull_tag.split('-')|last }}
|
||||
|
||||
.. list-table::
|
||||
:header-rows: 1
|
||||
@@ -40,7 +40,6 @@ For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.d
|
||||
|
||||
What's new
|
||||
==========
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
|
||||
|
||||
{% set docker = data.docker %}
|
||||
@@ -105,6 +104,22 @@ 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
|
||||
=================
|
||||
|
||||
@@ -311,7 +326,7 @@ Run inference
|
||||
|
||||
{% endif %}
|
||||
{% if model.model == "Wan2.1" %}
|
||||
cd Wan
|
||||
cd /app/Wan
|
||||
mkdir results
|
||||
|
||||
torchrun --nproc_per_node=8 /app/Wan/run.py \
|
||||
@@ -330,7 +345,7 @@ Run inference
|
||||
|
||||
{% endif %}
|
||||
{% if model.model == "Wan2.2" %}
|
||||
cd Wan
|
||||
cd /app/Wan
|
||||
mkdir results
|
||||
|
||||
torchrun --nproc_per_node=8 /app/Wan/run.py \
|
||||
@@ -350,7 +365,7 @@ Run inference
|
||||
{% endif %}
|
||||
|
||||
{% if model.model == "FLUX.1" %}
|
||||
cd Flux
|
||||
cd /app/Flux
|
||||
mkdir results
|
||||
|
||||
torchrun --nproc_per_node=8 /app/Flux/run.py \
|
||||
@@ -369,8 +384,54 @@ Run inference
|
||||
|
||||
{% 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 StableDiffusion3.5
|
||||
cd /app/StableDiffusion3.5
|
||||
mkdir results
|
||||
|
||||
torchrun --nproc_per_node=8 /app/StableDiffusion3.5/run.py \
|
||||
@@ -386,7 +447,7 @@ Run inference
|
||||
|
||||
{% 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 %}
|
||||
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 %}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user