FS-Attention

Hybrid attention inference IP

Native support for hybrid-attention large language models.

Data flow

Native support for hybrid-attention large language models.

Fig. 2 · FS-Attention data flow

Native support

Qwen3 / 3.5 (0.6B to 9B) and SmolLM2

Deployment

ASIC tape-out and FPGA prototyping, with interface and system adaptation per project.

Licence includes

Inference core IP, FPGA evaluation board, model mapping and interface adaptation, design-in support.

IP coverage, interfaces, resource usage, performance targets and licensing terms are evaluated per target device and model.

Tell us the target device, model and interfaces. We reply with IP coverage and an evaluation plan.