Files
hao-ai-lab-FastVideo/examples/inference/basic/basic_fasth3_spark.yaml

59 lines
1.8 KiB
YAML

# FastH3 on one DGX Spark (one GB10). Install: docs/getting_started/installation/spark.md
#
# GB10 has no FA4 / sm_100a VSA kernel. Keep the env prefix below, or pass
# equivalent CLI flags on examples/inference/basic/basic_fasth3.py
# (`--vsa-kernel triton --no-fa4 --num-gpus 1`).
#
# request.sampling below is an example, not a required recipe. Change height,
# width, num_frames, num_inference_steps, seed, and prompt. Legal H3 frame
# counts are 17n+5, max 345 (15 s). Native 16:9 sizes include 832x480 and
# 1344x768. 1024x576 is a common recipe-matched 16:9.
#
# FASTVIDEO_VSA_SM100A=0 FASTVIDEO_FA4=0 FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN_H3 \
# FASTVIDEO_STAGE_LOGGING=1 \
# fastvideo generate --config examples/inference/basic/basic_fasth3_spark.yaml
generator:
model_path: FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree
engine:
num_gpus: 1
use_fsdp_inference: false
parallelism:
tp_size: 1
sp_size: 1
offload:
dit: false
dit_layerwise: false
text_encoder: true
vae: true
pin_cpu_memory: true
lazy_module_load: true
compile:
enabled: false
vae_enabled: true
pipeline:
experimental:
attention_backend: VIDEO_SPARSE_ATTN_H3
VSA_sparsity: 0.9
VSA_tile_size: 64
inference_torch_compile: true
vae_parallel_decode: true
vae_parallel_decode_strategy: gather
request:
prompt: >-
A wide cinematic shot of an alpine meadow at sunrise, pale pink mountain
peaks above a blue valley filled with thin morning mist.
negative_prompt: ""
sampling:
seed: 2026
height: 768
width: 1344
num_frames: 124
fps: 24
num_inference_steps: 5
guidance_scale: 1.0
batch_cfg: false
output:
output_path: outputs/fasth3_spark/
save_video: true
return_frames: false