Spectrum forecasts DiT features and skips selected denoising steps. It is an
approximation: validate visual or video quality and latency on the exact model,
shape, hardware, and sampling settings you plan to deploy.
sglang generate \ --model-path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \ --prompt "A paper boat floating through a misty mountain lake" \ --enable-spectrum \ --save-output
Available on native FLUX.1, Wan, HunyuanVideo, SD3, and MiniMax-H3
implementation paths. It is not a --backend diffusers feature and does
not currently cover FLUX.2.
The request control is available through sglang generate and Python
sampling parameters. It is not a sglang serve or OpenAI-server request
option yet.
Spectrum and --enable-teacache are mutually exclusive. On MiniMax-H3
it also cannot run with Cache-DiT / quality="high", or with SP > 1.
MiniMax-H3 50-step recipe: --spectrum-warmup-steps 11 --spectrum-window-size 5 --spectrum-flex-window 1.0. Defaults are the
20-step schedule. See the MiniMax-H3 cookbook.
Start with the defaults. --debug adds shadow-prediction validation work,
so its latency is not representative of normal Spectrum execution.
Use --enable-spectrum explicitly. Providing any Spectrum override also
enables it, but that implicit behavior is intended for scripts rather than new
commands.
Flag
Default
Purpose
--spectrum-window-size
2.0
Initial step-skipping window
--spectrum-flex-window
0.75
Window growth after a real forward
--spectrum-warmup-steps
5
Initial exact DiT forwards
--spectrum-m
4
Chebyshev basis count
--spectrum-lam
0.1
Ridge regularization
--spectrum-tau-num-steps
50
Chebyshev time horizon
--history-size
100
Recent feature-history capacity
--taylor-order
1
Local predictor order (1, 2, or 3)
--w
1.0
Chebyshev/Taylor blend weight
These controls trade speed against output fidelity. Change one control at a
time and retain a lossless baseline for comparison.
Was this page helpful?
Assistant
Responses are generated using AI and may contain mistakes.
