Model Recipes

fluxserve launch \
  --model inclusionAI/LLaDA2.0-mini \
  --tp-size 1 \
  --dp-size 1 \
  --ep-size 1 \
  --attention-backend flashinfer

Model

Hardware

Variant

Full BF16 — single 80 GB NVIDIA GPU (H100/H200). Requires --max-num-seqs 4 to avoid OOM from diffusion state buffers.

Attention Backend

Parallelism Settings

Hardware selects the target label; FluxServe detects the installed GPU. Adjust the checkpoint in the command as needed.

See Configuration for all serving parameters.