arXiv subjects

Xinkui Zhao

Publications and source records attributed to Xinkui Zhao.

3 recordsLinked to original sources

arXiv2026

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers

Diffusion Transformers (DiTs) are costly at high resolution because self-attention scales quadratically with token sequence length. Existing pruning methods do not jointly provide end-to-end learnability, low training overhead, and deterministic token counts for predictable token-dependent computation. We propose Shiva-DiT, based on Residual-Based Differentiable Top-k Selection. Its forward pass executes hard top-k selection, while a residual-aware straight-through estimator propagates gradients to both token scores and the budget k without evaluating a second backbone path. A Context-Aware Router and Adaptive Ratio Policy learn layer- and timestep-dependent retention schedules under a target average budget. Experiments on SD3-Medium, Flux.1-dev, and PixArt-Σ show consistent reductions in FLOPs and measured latency. On SD3-Medium, Shiva-DiT provides four fidelity-latency operating points and reaches a 1.54x wall-clock speedup with competitive fidelity.

cs.LG↗

arXiv2026

Prediction-Robust Service Deployment with Capacity-Aware Edge Admission

Edge platforms instantiate executable services close to users to reduce request-serving cost, but each instance incurs a one-time deployment cost and remains useful only for a finite time-to-live (TTL). The resulting online decision is both prediction-sensitive and capacity-coupled: an optimistic forecast can waste deployment cost, whereas a delayed decision misses the burst it is intended to serve. We study this problem under a common TTL cost model and propose CAPSUM, a capacity-aware admission policy with an elastic specialization, CAPSUM-E. In the local elastic setting, every node-service trace is exactly a variable-price Bahncard instance. This reduction lets CAPSUM-E inherit PFSUM's tight prediction-error-dependent ratio, including $2/(1+β)$ consistency and $1/β$ robustness for $β>0$. A redirect-aware variant preserves the same local deployment schedule. For finite-capacity nodes, CAPSUM combines size-scaled break-even tests, a utilization-dependent shadow price, and evidence-density eviction; we prove capacity feasibility, scale invariance, and exact agreement with CAPSUM-E under an elastic configuration. We implement an exact local offline dynamic program and compare against direct common-model baselines and documented source-derived adapters for EDP-A, OREO, and uEDC-L. Experiments cover controlled prediction error, three synthetic demand regimes, a causal predictor on a public Globus Compute trace, and joint scaling to 1,024 nodes and 10,000 services. Under the common model, CAPSUM reduces normalized cost by 33.7-42.9% relative to the best source-derived adapter across the synthetic regimes and by 45.5% on the sampled trace.

cs.DC↗

arXiv2026

Measurement-Driven Diagnosis and Mitigation of Host-CPU Co-location Interference in Single-GPU LLM Serving on a Multi-GPU Server

Host CPUs in GPU servers are often under-used during LLM inference. Co-locating CPU workloads can improve resource use, but it can also seriously hurt serving quality. Existing work mainly improves LLM serving engines or studies CPU-GPU boundary delays. It gives limited guidance on how external CPU workloads affect the serving path and how operators should choose protection policies. This paper studies host-CPU co-location interference in single-GPU LLM serving. We show that the main observed problem is not slower GPU kernels. Instead, CPU workloads amplify long tails in CPU-side serving stages before GPU work is submitted. To capture this effect, we introduce the Core Path Tail Index (CPTI) and Core Tail Suppression (CTS). Based on these metrics, we build CoTail, a measurement-driven diagnostic procedure that screens workload risk, profiles serving-stage tails, selects OS-level protections, and validates decode SLO compliance. In our primary setup, unprotected nginx co-location reduces throughput by 78.8%, increases TTFT by 429.5%, and increases TPOT by 362.4%. CoTail-guided protections improve nginx throughput by up to 4.4x and reduce TPOT by 4.5x. Under a common-baseline deployment SLO, CoTail satisfies all 12 oracle-feasible held-out cases, compared with 10/12 for Always-rt and 11/12 for Macro-only. It also reduces RT usage from 28 to 22 cases and lowers mean co-tenant slowdown from 56.65% to 51.21%.

cs.DC↗