Davids048andClaude Opus 5.5
ecb15bf9e0
Every key that repository YAML configs, Python examples, the Dreamverse backend, and tests passed through pipeline.experimental has a typed GeneratorConfig field, so they use those fields instead: engine.attention, engine.compile.regional, pipeline.flow_shift, pipeline.embedded_cfg_scale, pipeline.dmd_denoising_steps, pipeline.components.lora_nickname, pipeline.minimax_h3, and pipeline.longcat. No repository config outside the tests uses pipeline.experimental any more. The flat FastVideoArgs keywords that each migrated YAML file and each basic_fasth3.py option set produces match the previous ones. The golden snapshots of the two Hunyuan scripts now record embedded_cfg_scale and flow_shift as floats (6.0 instead of 6), because the typed fields are floats. The guidance tensor is built as float32 either way. The golden case untyped_experimental_keys is renamed attention_precision_and_flow_shift with identical content, and keys_without_typed_fields covers keywords that still go to pipeline.experimental. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012M91wnVFmPEvJ9h39r5BH7
60 lines
1.8 KiB
YAML
60 lines
1.8 KiB
YAML
# FastH3 on two DGX Sparks (one GPU each) over QSFP RoCE.
|
|
# Bring up the Ray cluster first: docs/getting_started/installation/spark_pair.md
|
|
#
|
|
# 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).
|
|
#
|
|
# source examples/inference/optimizations/spark_pair_env.sh
|
|
# export RAY_ADDRESS=<qsfp-head>:6379
|
|
# export FASTVIDEO_HOST_IP=<qsfp-head>
|
|
# FASTVIDEO_VSA_SM100A=0 FASTVIDEO_FA4=0 FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN_H3 \
|
|
# FASTVIDEO_VAE_PARALLEL_DECODE=1 FASTVIDEO_STAGE_LOGGING=1 \
|
|
# fastvideo generate --config examples/inference/basic/basic_fasth3_spark_pair.yaml
|
|
generator:
|
|
model_path: FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree
|
|
engine:
|
|
num_gpus: 2
|
|
execution_backend: ray
|
|
use_fsdp_inference: false
|
|
parallelism:
|
|
tp_size: 1
|
|
sp_size: 2
|
|
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
|
|
regional: true
|
|
attention:
|
|
backend: VIDEO_SPARSE_ATTN_H3
|
|
vsa_sparsity: 0.9
|
|
vsa_tile_size: 64
|
|
pipeline:
|
|
minimax_h3:
|
|
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_pair/
|
|
save_video: true
|
|
return_frames: false
|