Research map / Architectures and efficiency / RNNs and normalization
RTInfer: Real-Time Inference of Multiple DNNs on Edge GPUs
Renjie Li, Tong Sun, Yi Gao, Wei Dong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add accuracy-calibrated lightweight variant co-optimization (ALC) (ablation) | RTInfer · Ablation (Robot, UAV, Traffic) | DMR: removing it elevates DMR by about 2× | Improved |
| add memory-layout-aware scheduler (MS) (ablation) | RTInfer · Ablation (Robot, UAV, Traffic) | DMR: disabling it increases DMR by 2–3× | Improved |
| add Delta-Graph load-aware pipeline (DLP) (ablation) | RTInfer · Ablation (Robot, UAV, Traffic) | DMR: omitting it elevates DMR by 3–6× | Improved |
| RTInfer instead of Pantheon under tight deadlines | Pantheon · Edge multi-DNN apps, deadline scale 0.6-0.8 | DMR: 27.6 -> 0 | Improved |
| looser deadlines narrow the gap to Pantheon | RTInfer · Edge multi-DNN apps, deadline scale 1.2-1.4 | DMR/accuracy | No clear effect |
| RTInfer instead of Pantheon runtime power | Pantheon · Power on Jetson | average power (W): 8.80 -> 9.56 | Hurt |
Closest papers by meaning
- HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained Devices (NeurIPS 2026 · similarity 0.85)
- Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving (ICML 2025 · similarity 0.84)
- Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters (AAAI 2025 · similarity 0.84)
- FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision (NeurIPS 2024 · similarity 0.83)
- E4: Energy-Efficient DNN Inference for Edge Video Analytics via Early Exiting and DVFS (AAAI 2025 · similarity 0.82)
- ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
