mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-09-30 20:37:25 +00:00
17fd819a0e
* archive previous version * Update components version * Update run settings for a few models * Update hf download and pull tag * ROCm bump and what's new * Fix double (preview) (preview) text * update --------- Co-authored-by: Kristoffer Torp <[email protected]>
364 lines
14 KiB
YAML
364 lines
14 KiB
YAML
docker:
|
|
pull_tag: rocm/pytorch-xdit:v26.5
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v26.5/images/sha256-b8ad9fd4b41bc116ac2aff07c1066bf369cf7fc110b1a323f6302191985a51fd
|
|
ROCm: 7.13.0
|
|
whats_new:
|
|
- "Hunyuan Video 1.5 sparse attention (SSTA) support"
|
|
- "Support fp8 MLA for MI355"
|
|
- "Block wise sparsity support for AMD triton FAv3 Sage attention"
|
|
components:
|
|
TheRock:
|
|
version: cbff3d1
|
|
url: https://github.com/ROCm/TheRock
|
|
rocm-libraries:
|
|
version: a668483b
|
|
url: https://github.com/ROCm/rocm-libraries
|
|
rocm-systems:
|
|
version: c76140fa
|
|
url: https://github.com/ROCm/rocm-systems
|
|
torch:
|
|
version: ff65f5b
|
|
url: https://github.com/ROCm/pytorch
|
|
torchaudio:
|
|
version: e3c6ee2
|
|
url: https://github.com/pytorch/audio
|
|
torchvision:
|
|
version: b919bd0
|
|
url: https://github.com/pytorch/vision
|
|
triton:
|
|
version: a272dfa
|
|
url: https://github.com/ROCm/triton
|
|
accelerate:
|
|
version: 46ba481
|
|
url: https://github.com/huggingface/accelerate
|
|
aiter:
|
|
version: bc5ea32c
|
|
url: https://github.com/ROCm/aiter
|
|
diffusers:
|
|
version: 447e571a
|
|
url: https://github.com/huggingface/diffusers
|
|
distvae:
|
|
version: 5a0fcbb
|
|
url: https://github.com/xdit-project/DistVAE
|
|
xfuser:
|
|
version: 051db68f
|
|
url: https://github.com/xdit-project/xDiT
|
|
yunchang:
|
|
version: 631bdfd
|
|
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
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--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_calls 1 \'
|
|
- '--num_iterations 1 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--enable_tiling --enable_slicing \'
|
|
- '--guidance_scale 6.0 \'
|
|
- '--use_torch_compile \'
|
|
- '--attention_backend aiter \'
|
|
- '--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:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--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_iterations 1 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--enable_tiling --enable_slicing \'
|
|
- '--use_torch_compile \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- 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
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--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." \'
|
|
- '--height 720 \'
|
|
- '--width 1280 \'
|
|
- '--input_images /app/data/wan_input.jpg \'
|
|
- '--num_frames 81 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_parallel_vae \'
|
|
- '--seed 42 \'
|
|
- '--guidance_scale 3.0 \'
|
|
- '--num_iterations 1 \'
|
|
- '--num_inference_steps 40 \'
|
|
- '--use_torch_compile \'
|
|
- '--attention_backend aiter \'
|
|
- '--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:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--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." \'
|
|
- '--height 720 \'
|
|
- '--width 1280 \'
|
|
- '--input_images /app/data/wan_input.jpg \'
|
|
- '--num_frames 81 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_parallel_vae \'
|
|
- '--seed 42 \'
|
|
- '--num_iterations 1 \'
|
|
- '--num_inference_steps 40 \'
|
|
- '--use_torch_compile \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- 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
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--seed 42 \'
|
|
- '--prompt "A small cat" \'
|
|
- '--height 1024 \'
|
|
- '--width 1024 \'
|
|
- '--num_inference_steps 25 \'
|
|
- '--max_sequence_length 256 \'
|
|
- '--warmup_calls 5 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--guidance_scale 0.0 \'
|
|
- '--num_iterations 50 \'
|
|
- '--attention_backend aiter \'
|
|
- '--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:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--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_calls 5 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--input_images /app/data/flux_cat.png \'
|
|
- '--guidance_scale 2.5 \'
|
|
- '--num_iterations 25 \'
|
|
- '--attention_backend aiter \'
|
|
- '--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:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--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_calls 5 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--input_images /app/data/flux_cat.png \'
|
|
- '--guidance_scale 4.0 \'
|
|
- '--num_iterations 25 \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- model: FLUX.2 Klein
|
|
model_repo: black-forest-labs/FLUX.2-klein-9B
|
|
url: https://huggingface.co/black-forest-labs/FLUX.2-klein-9B
|
|
github: https://github.com/black-forest-labs/flux2
|
|
mad_tag: pyt_xdit_flux_2_klein
|
|
js_tag: flux_2_klein_tag
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--seed 42 \'
|
|
- '--prompt "A spectacular sunset over the ocean" \'
|
|
- '--height 2048 \'
|
|
- '--width 2048 \'
|
|
- '--num_inference_steps 4 \'
|
|
- '--warmup_calls 5 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--guidance_scale 1.0 \'
|
|
- '--num_iterations 25 \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- 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
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--prompt "A capybara holding a sign that reads Hello World" \'
|
|
- '--num_iterations 50 \'
|
|
- '--num_inference_steps 28 \'
|
|
- '--pipefusion_parallel_degree 4 \'
|
|
- '--use_cfg_parallel \'
|
|
- '--use_torch_compile \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- group: Z-Image
|
|
js_tag: z_image
|
|
models:
|
|
- model: Z-Image
|
|
model_repo: Tongyi-MAI/Z-Image
|
|
url: https://huggingface.co/Tongyi-MAI/Z-Image
|
|
github: https://github.com/Tongyi-MAI/Z-Image
|
|
mad_tag: pyt_xdit_z_image
|
|
js_tag: z_image_tag
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--seed 42 \'
|
|
- '--prompt "A crowded beach" \'
|
|
- '--height 1088 \'
|
|
- '--width 1920 \'
|
|
- '--num_inference_steps 50 \'
|
|
- '--ulysses_degree 2 \'
|
|
- '--ring_degree 2 \'
|
|
- '--use_cfg_parallel \'
|
|
- '--use_torch_compile \'
|
|
- '--guidance_scale 4.0 \'
|
|
- '--num_iterations 25 \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- group: LTX
|
|
js_tag: ltx
|
|
models:
|
|
- model: LTX-2
|
|
model_repo: Lightricks/LTX-2
|
|
url: https://huggingface.co/Lightricks/LTX-2
|
|
github: https://github.com/Lightricks/LTX-2
|
|
mad_tag: pyt_xdit_ltx2
|
|
js_tag: ltx2_tag
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--seed 42 \'
|
|
- '--prompt "Cinematic action packed shot. The man says silently: \"We need to run.\". The camera zooms in on his mouth then immediately screams: \"NOW!\". The camera zooms back out, he turns around and bolts it." \'
|
|
- '--height 1088 \'
|
|
- '--width 1920 \'
|
|
- '--num_inference_steps 40 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--guidance_scale 4.0 \'
|
|
- '--num_iterations 1 \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- group: Qwen-Image
|
|
js_tag: qwen_image
|
|
models:
|
|
- model: Qwen-Image
|
|
model_repo: Qwen/Qwen-Image-2512
|
|
url: https://huggingface.co/Qwen/Qwen-Image-2512
|
|
github: https://github.com/QwenLM/Qwen-Image
|
|
mad_tag: pyt_xdit_qwen_image
|
|
js_tag: qwen_image_tag
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--seed 42 \'
|
|
- '--prompt "A cat holding a sign that says hello world" \'
|
|
- '--height 2048 \'
|
|
- '--width 2048 \'
|
|
- '--num_inference_steps 50 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--guidance_scale 0.0 \'
|
|
- '--num_iterations 25 \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|
|
- model: Qwen-Image-Edit
|
|
model_repo: Qwen/Qwen-Image-Edit
|
|
url: https://huggingface.co/Qwen/Qwen-Image-Edit
|
|
github: https://github.com/QwenLM/Qwen-Image
|
|
mad_tag: pyt_xdit_qwen_image_edit
|
|
js_tag: qwen_image_edit_tag
|
|
benchmark_command:
|
|
- mkdir results
|
|
- 'xdit \'
|
|
- '--model {model_repo} \'
|
|
- '--seed 42 \'
|
|
- '--prompt "Add a cool hat to the cat." \'
|
|
- '--negative_prompt "" \'
|
|
- '--input_images /app/data/flux_cat.png \'
|
|
- '--height 2048 \'
|
|
- '--width 2048 \'
|
|
- '--num_inference_steps 50 \'
|
|
- '--ulysses_degree 8 \'
|
|
- '--use_torch_compile \'
|
|
- '--guidance_scale 4.0 \'
|
|
- '--num_iterations 25 \'
|
|
- '--attention_backend aiter \'
|
|
- '--output_directory results'
|