Speculation at a Distance: Where Edge-Cloud Speculative Decoding Actually Pays Off
For practitioners considering edge-cloud LLM deployment, the paper provides theoretical bounds showing DSD is primarily beneficial for server throughput rather than single-request latency.
The paper analytically shows that distributed speculative decoding (DSD) with edge draft and cloud target models offers limited latency benefit under WAN conditions compared to co-located SD, but can improve multi-tenant server capacity by offloading draft compute.
Speculative decoding (SD) accelerates LLM inference by $1.5$-$3$ times when the draft and target models are co-located. This has motivated a distributed variant (DSD) that places the draft model on an edge device while the target stays in the cloud. We show with closed-form inequalities that DSD's per-request latency benefit is limited under WAN edge-cloud communication. If the server can host both models, co-located SD has lower latency and communication than synchronous DSD, with the same per-output FLOPs and model-weight memory. Pipelining can make DSD competitive with co-located SD only in low-RTT regimes where the round trip is shorter than the edge drafting time window; at WAN RTTs, the cloud round trip remains too large for pipelined DSD to beat co-located SD. Against cloud autoregressive decoding, DSD can reduce latency only inside a bounded window given the target-model speed, acceptance rate, and RTT. DSD is also infeasible against closed-source APIs without a verifier-only interface. The main case for DSD appears in multi-tenant capacity. Under cross-client overlap, offloading draft compute lets a saturated cloud server sustain $(1 + γ\,t_d/t_v)$ times more concurrent clients at the same per-client rate, where $γ$ is the speculation length and $t_d, t_v$ are the per-step draft and verification times. DSD should therefore be evaluated primarily by multi-tenant capacity and server throughput, not only by single-request latency.