EdgeDAE uses FPGA-GPU heterogeneous acceleration of diffusion action experts
Understand this story
Zhiheng Chen et al. submitted a paper proposing EdgeDAE, a heterogeneous FPGA-GPU system for accelerating diffusion action expert (DAE) inference. The system partitions workloads by computational characteristics: the vision Transformer remains running on the GPU, while DAE inference is offloaded to the FPGA. The paper states that on the FPGA side, all parameters are stored on-chip in BRAM/URAM to eliminate memory access bottlenecks. This design targets real-time physical AI scenarios; the paper does not provide measured speedup or accuracy results.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIEdgeDAE: Acceleration of Diffusion Action Experts for Real-Time Physical AI
EdgeDAE is a heterogeneous FPGA-GPU system that offloads the perception-heavy vision transformer to the GPU while accelerating Diffusion Action Expert (DAE) inference on an FPGA by storing all parameters on-chip in BRAM/URAM, eliminating the repeated DRAM parameter loading of iterative denoising. It co-designs quantization, fixed-point arithmetic, and hardware-efficient random number generation for the FPGA fabric. Compared with an edge GPU baseline, it reduces end-to-end inference latency by 52.5% for Octo-Small and 38.7% for Octo-Base with up to 2.10x higher throughput, and achieves about 17x higher energy efficiency than an RTX 4090.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 22:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.