This work presents a distributed inference framework that integrates speculative decoding across edge and cloud, and shifts the bulk of computation to the edge, significantly lowers inference time and cloud cost, and preserves the accuracy of the big model without any retraining requirement.
Abstract
Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational demands. Deploying smaller LLMs directly on the edge can circumvent this, but with degraded accuracy. Deploying smaller cloud-based big LLMs preserves performance, but at the cost of expensive per-token computation. We present a distributed inference framework, \our{}, that integrates speculative decoding (SD) across edge and cloud. A compact draft model deployed on the edge generates candidate tokens rapidly, and a large verifier model on the cloud validates these tokens in parallel. Accepted tokens are retained, while only rejections trigger verifier correction, substantially reducing the number of cloud queries. Our plug-and-play design shifts the bulk of computation to the edge, significantly lowers inference time and cloud cost, and preserves the accuracy of the big model without any retraining requirement. Our approach demonstrates a practical path toward scalable, cost-efficient, and accurate deployment of LLMs in real-world environments. Experimental results across multiple Natural Language Processing tasks using SpecBench and CNN/Dailymail datasets demonstrate that \our{} reduces the cloud model calls by $76\%$ with zero loss in accuracy as compared to the full model.
Results show that DEFRAG narrows the SLM-LLM accuracy gap, while reducing cost by up to 98.4% and increasing peak throughput by up to 97.8% over centralized services, demonstrating the potential of DEFRAG for democratized LLM services at the edge.
Jiaxing Li, Hengzhi Wang, Feng Wang et al.· IEEE Transactions on Mobile...· 0 citations
Large language model (LLM) agents repeatedly process long, privacy-sensitive contexts, while cloud-only deployment exposes user data beyond the trusted endpoint and fully local deployment often requires costly hardware. Split inference offers a middle ground by executing the model head, tail, and tools locally and the middle layers in the cloud, but its local-cloud-local path transfers boundary hidden states at every invocation and creates a critical communication bottleneck. We present \system, a reference-aware codec that retrieves exact-token historical spans for prefill uplinks, reuses the reconstructed uplink state for same-round prefill downlinks, and generates boundary-specific decode references with lightweight causal predictors. RAC applies grouped affine alignment and calibrated residual quantization with optional prefill outliers, while sender-side wire-format reconstruction synchronizes subsequent references and offline calibration accounts for quality and packed representation costs. Across three models and nine evaluated model-link pairs, Raw-to-RAC mean time to first token (TTFT) and time per output token (TPOT) ratios are 1.24-2.72$\times$ and 1.01-2.79$\times$, while the 12 non-perplexity task-score changes range from $-0.40$ to $+2.50$ points.
Guotao Yang, M. Zhao, Haopeng Li et al.· 0 citations
The rise of reasoning models and agentic systems has made LLM token-generation latency a key bottleneck. Unlike chatbots, whose latency gains saturate at human reading speed, these systems generate intermediate reasoning tokens not consumed by humans. Thus, per-token latency directly determines end-to-end response time. Low-latency inference uses minimal batching, making token generation bandwidth-bound. Tensor Parallelism addresses this by sharding model weights across GPUs and loading them in parallel. However, scaling to more GPUs introduces All-Reduce overheads that grow with GPU count. Removing All-Reduce improves token throughput by 43% for Llama-3.1-8B on 8 H200 GPUs. We propose Synchronization-Free All-Reduce (SiFAR), which reduces synchronization overhead during low-latency inference. Existing oneshot and twoshot algorithms incur overheads from barriers before and after communication. First, we find that the bottom barrier in oneshot enforces a WAW dependency and eliminate it by co-designing communication and model execution to enable dual buffering. However, oneshot scales poorly with GPU count. Twoshot performs better at higher TP degrees but incurs an unavoidable bottom barrier. To overcome this, we leverage in-switch reduction in modern switches. We propose redundant pull, where each GPU reduces the full All-Reduce payload at the switch. This improves oneshot scalability while retaining its no-bottom-barrier advantage. Finally, to reduce top-barrier overhead, we observe that each decode step issues multiple All-Reduce operations, keeping GPUs tightly synchronized after the first. We therefore propose speculative reduction, which initiates data transfer before the top barrier and ensures correctness via lightweight validation. SiFAR reduces All-Reduce latency by up to 52% and improves end-to-end throughput by 18.6% for Llama-3.1-8B and 13.1% for Qwen3.5-397B-17B at TP=8.
Hritvik Taneja, A. Saxena, Abhishek Revinipati et al.· 1 citation
This work presents AsymSpec, which addresses uplink-gated verification and invalid dependent work with two corresponding mechanisms, and shows that AsymSpec delivers 2.82-28.03$\times the output-token throughput of the strongest baseline.
Guotao Yang, Hao Chen, Rui Guo et al.· 0 citations
DABO is proposed, a calibration-aware binary offloading method for collaborative large–small model inference that maintains competitive end-to-end accuracy while processing an average of 83.72% of requests at the edge.
Chen Zhu, Yi-Ming Su, Chenwenjie Mao et al.· IEEE Access· 0 citations
EPIC mitigates imbalance via performance-aware expert migration and runtime expert activation, and then improves communication with topology-adaptive transport kernels and fine-grained computation-communication overlap.
Jiamin Cao, Qingxu Li, Yaozhong Liu et al.· Proceedings of the ACM SIGCO...· 0 citations