Built for Variable Lengths
Block-causal attention handles variable-length prefill and decoding efficiently, with native FlashInfer and FA4 support
FluxServeFlexible and High-Performance
Diffusion LLM Inference.
Open-source, high-throughput and cost-effectient dLLM serving engine for everyone.
INSIDE FLUXSERVE
Built for the way diffusion generates
Keep the Pipeline Moving
Fine-grained, block-level scheduling keeps requests flowing across the C++ control plane and Python execution path
Scale Beyond One GPU
Tensor, data, and expert parallelism extend diffusion inference across multi-GPU deployments