Speeding up inference for Wan2.2-VACE-fun-A14B, sage-attention and batch inference?

I have been running multi-gpu inference for Wan-2.2-VACE for resolution of 512x512 videos with 121 frames.
It takes about 50 seconds to do 20 diffusion steps on 8xH200s, using this config:

ulysses_degree      = 4
ring_degree         = 2
fsdp_dit            = False
fsdp_text_encoder   = True
compile_dit         = True

enable_teacache     = True
teacache_threshold  = 0.10
num_skip_start_steps = 5
teacache_offload    = False

cfg_skip_ratio      = 0.1

# Riflex config
enable_riflex       = False
# Index of intrinsic frequency
riflex_k            = 6

# Config and model path
config_path         = "config/wan2.2/wan_civitai_t2v.yaml"
# model path
model_name          = "models/Diffusion_Transformer/Wan2.2-VACE-Fun-A14B"

# Choose the sampler in "Flow", "Flow_Unipc", "Flow_DPM++"
sampler_name        = "Flow"
# [NOTE]: Noise schedule shift parameter. Affects temporal dynamics. 
# Used when the sampler is in "Flow_Unipc", "Flow_DPM++".
shift               = 12.0

# Other params
sample_size         = [512, 512]
video_length        = 121
fps                 = 60

weight_dtype        = torch.bfloat16
control_video       = "outputs-1/input_videos/1.mp4"
start_image         = None
end_image           = None
# Use inpaint video instead of start image and end image.
inpaint_video       = None
inpaint_video_mask  = None
subject_ref_images  = None
vace_context_scale  = 1.00
padding_in_subject_ref_images   = True

guidance_scale          = 5.0
seed                    = 43
num_inference_steps     = 20

It is possible to use sage-attention with the model?
I tried flash attention but it did not offer any speedups compared to torch SDPA,
I installed sage attention but the model does not seem to be using it.

Is it possible to do batch inference (i.e. generating two videos using 2 differenct control videos on the same GPU since, max memory util is 70GB on H200?

Start from the supplied Wan2.2-VACE configuration and the current torch SDPA, flash-attention, and sage-attention setup. Measure the existing 20-step, 512x512, 121-frame run on 8xH200s, then investigate whether attention selection and two-video batch inference are supported. Done means documenting or implementing a verified speedup and confirming memory and output behavior.