376e445f0e
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
65 lines
2.1 KiB
YAML
65 lines
2.1 KiB
YAML
# FastH3 V2 eight-forward video+audio on one DGX Spark.
|
|
# Download the complete release checkpoint as described in
|
|
# docs/getting_started/installation/spark_performance.md.
|
|
#
|
|
# FP4 attention needs fastvideo-kernel built for 12.1a and eager DiT inference.
|
|
# A missing extension is an error. Set h3_vsa_fp4.enabled to false for BF16 VSA.
|
|
# The NVFP4 encoder and lightweight VAE ship in the same repository.
|
|
#
|
|
# FASTVIDEO_H3_VSA_FP4=1 FASTVIDEO_MINIMAX_H3_FUSIONS=all FASTVIDEO_NVFP4_MM_BACKEND=cudnn FASTVIDEO_NVFP4_MM_ROW_SPLIT=table \
|
|
# FASTVIDEO_H3_VAE_TILE_BATCH=12 FASTVIDEO_H3_VAE_INT8_OVERLAY=0 \
|
|
# FASTVIDEO_VSA_TRITON=1 FASTVIDEO_VSA_PTX_BLACKWELL=0 FASTVIDEO_FA4=0 \
|
|
# FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN_H3 FASTVIDEO_STAGE_LOGGING=1 \
|
|
# fastvideo generate --config examples/inference/basic/basic_fasth3_spark_v2_nvfp4.yaml
|
|
generator:
|
|
model_path: FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4-Consumer
|
|
engine:
|
|
num_gpus: 1
|
|
use_fsdp_inference: false
|
|
quantization:
|
|
transformer_quant: NVFP4
|
|
layer_profile: h3_dit_vsa
|
|
parallelism:
|
|
tp_size: 1
|
|
sp_size: 1
|
|
offload:
|
|
dit: false
|
|
dit_layerwise: false
|
|
text_encoder: false
|
|
image_encoder: false
|
|
vae: false
|
|
pin_cpu_memory: false
|
|
lazy_module_load: false
|
|
compile:
|
|
enabled: false
|
|
vae_enabled: true
|
|
pipeline:
|
|
workload_type: t2v
|
|
vae_tiling: true
|
|
experimental:
|
|
attention_backend: VIDEO_SPARSE_ATTN_H3
|
|
h3_vsa_fp4:
|
|
enabled: true
|
|
VSA_sparsity: 0.8
|
|
VSA_tile_size: 64
|
|
h3_sequential_load: false
|
|
inference_torch_compile: false
|
|
vae_parallel_decode: false
|
|
video_decode_backend: h3-vae
|
|
request:
|
|
prompt: A quiet pottery studio with a potter finishing a bowl at the wheel.
|
|
negative_prompt: ""
|
|
sampling:
|
|
seed: 1234
|
|
height: 480
|
|
width: 832
|
|
num_frames: 124
|
|
fps: 24
|
|
num_inference_steps: 9 # nine sigma points, eight DiT forwards
|
|
guidance_scale: 1.0
|
|
batch_cfg: false
|
|
output:
|
|
output_path: outputs/fasth3_spark_v2_nvfp4/
|
|
save_video: true
|
|
return_frames: false
|