arXiv subjects

Jiakun Fan

Publications and source records attributed to Jiakun Fan.

9 recordsLinked to original sources

arXiv2026

Rethinking KV Cache Eviction for Agentic LLM Serving

Key-value (KV) caches impose substantial memory pressure on large language model serving systems, requiring cache eviction when capacity is insufficient. Existing mechanisms typically evict KV from the ends of cached sequences to preserve prefix sharing across requests. However, agent workloads repeatedly reuse long histories across successive turns. Recomputing the KV cache for tokens near the end of a sequence is substantially more expensive than for earlier tokens because their attention computation involves longer histories. To address this problem, we propose preserving shared prefixes and evicting the KV cache from the beginning of the remaining history while retaining the cached suffix. We build Penelope around this strategy by co-designing the eviction policy, KV recomputation, and unified GPU-CPU cache management. Returning requests reuse the KV cache retained in GPU or CPU memory and recompute only missing segments while preserving reuse of the cached suffix. We implement Penelope in SGLang and evaluate it on three Qwen3 model sizes using real agent traces. Compared with SGLang, Penelope reduces mean time to first token by up to 60% and job completion time by up to 37% with a GPU-only cache, and by up to 76% and 60% with a two-tier GPU-CPU cache.

cs.DC↗

arXiv2026

Athanor: An Agent-Native System for Autonomous Post-Training Research

Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence. We study a weaker form that can be measured today: frontier agents post-training a small raw base model with public data, as a test of their research potential. We build Athanor, an open agent-native system for autonomous post-training research (AutoPostTrain) on real GPUs. We give the agents full research autonomy, low-friction engineering tools, and efficient starter code. The agents carry out the research themselves: they read datasets and evaluation results, build their training data, write and modify training algorithms, tune hyperparameters, and analyze the results to decide what to try next. They work in a sandbox and cannot use external teacher models. Athanor's services supply frozen evaluation, managed jobs, decontaminated data, a persistent research record, and a held-out suite the agents are unaware of. In a 104-hour campaign, a team of four Claude Opus 5.5 agents, each on an eight-GPU node and given no research advice, improves Qwen3-4B-Base from 15.9 to 67.3 on a six-task development suite and from 9.2 to 48.2 on a held-out suite, against 66.5 and 47.9 for the official Qwen3-4B-Instruct-2507. To our knowledge, this is the first demonstration that a team of frontier agents can autonomously post-train a raw base model into a cross-domain generalist model that matches or surpasses the official instruct version on average. The campaign's full record shows that the agents reach this level by recombining known methods and each other's models: SFT on public reasoning data, RL with a rollout change one agent introduced, weight merges across agents, and rounds of self-distillation. With execution handled, today's agents already have the engineering and research ability to conquer this task. We hope Athanor provides a foundation for scaling autonomous AI research.

cs.AI↗

arXiv2026

Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding

Speculative decoding accelerates large language model inference through parallel verification of tokens proposed by a drafter. Diffusion drafters further parallelize proposal generation, but greater proposal capacity or higher mean accepted tokens (MAT) need not yield higher throughput. Because verification accepts only a consecutive prefix, early rejections can render later correct predictions ineffective, limiting MAT gains, while even higher MAT may not improve throughput if per-round latency increases. We introduce DScout, which uses two complementary factorizations to guide diffusion drafter training and inference for higher throughput. For training, DScout factorizes position-wise loss into inclusion, weighting, and prediction loss. This guides the design and combination of mixed-horizon training, intra-block unmasking, and acceptance-weighted loss to align supervision with prefix acceptance and improve MAT. For inference, DScout factorizes throughput as the ratio of MAT to per-round latency, guiding target-conditioning depth, drafter depth, and inference block size selection to identify a high-throughput configuration for each workload. Across six benchmarks, DScout achieves $3.84\times$ and $4.14\times$ mean speedups over autoregressive decoding on Qwen3-4B and Qwen3-8B, respectively, improving mean speedup over the state-of-the-art baseline by 9.1% and 7.1%. Across models and concurrency settings, our inference configuration policy provides up to 9.75% additional mean speedup over DScout's fixed configuration.

cs.LG↗

arXiv2026

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations. We present a systematic characterization of OS-level resource dynamics in sandboxed AI coding agents, analyzing 144 software engineering tasks from the SWE-rebench benchmark across two LLM models. Our measurements reveal that (1) OS-level execution (tool calls, container and agent initialization) accounts for 55-60% of end-to-end task latency; (2) memory, not CPU, is the concurrency bottleneck; (3) memory spikes are tool-call-driven with a up to 15.4x peak-to-average ratio; and (4) resource demands are highly unpredictable across tasks, runs, and models. Comparing these characteristics against serverless, microservice, and batch workloads, we identify three mismatches in existing resource controls: a granularity mismatch (container-level policies vs. tool-call-level dynamics), a responsiveness mismatch (user-space reaction vs. sub-second unpredictable bursts), and an adaptability mismatch (history-based prediction vs. non-deterministic stateful execution). We propose AgentCgroup, an intent-driven eBPF-based resource controller that exploits agents ability to declare resource needs and reconstruct execution strategies, using hierarchical cgroup structures aligned with tool-call boundaries, in-kernel enforcement via sched_ext and memcg_bpf_ops, and runtime-adaptive policies. Preliminary evaluation demonstrates improved multi-tenant isolation and reduced resource waste. AgentCgroup is open-source at https://github.com/eunomia-bpf/agentcgroup

cs.OS↗

arXiv2026

ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving

Speculative decoding enables collaborative Large Language Model (LLM) inference across cloud and edge by separating lightweight token drafting from heavyweight verification. While prior systems show performance and cost benefits, practical deployment requires navigating a large configuration space spanning draft model variants, quantisation levels, speculative lengths, and heterogeneous edge devices. This paper presents ConfigSpec, a configurationselection framework for distributed speculative LLM serving. ConfigSpec profiles edge devices and draft-target alignment, and models drafting throughput, acceptance rate, and power to evaluate goodput, verification cost efficiency, and energy efficiency across the joint configuration space. Our analysis across three edge platforms and two LLM families reveals structurally conflicting optima. Firstly, goodput is maximised by the smallest, fastest draft model at device-dependent speculative lengths (K*=2-10). Secondly, both cost and energy efficiency converge to K=2 due to a dominant bonus-token effect-with cost favouring the largest drafter for its high acceptance rate and energy favouring the smallest for its low power draw. These conflicts confirm that no single fixed configuration can simultaneously optimise all objectives, underscoring the need for profiling-based configuration selection in disaggregated edge-cloud LLM inference.

cs.DC↗

arXiv2026

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching

As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of inference requests are initiated from edge devices and computed on centralized GPU clusters. However, the resulting exponential growth in computation workload is placing significant strain on data centers, while edge devices remain largely underutilized, leading to imbalanced workloads and resource inefficiency across the network. Integrating edge devices into the LLM inference process via speculative decoding helps balance the workload between the edge and the cloud, while maintaining lossless prediction accuracy. In this paper, we identify and formalize two critical bottlenecks that limit the efficiency and scalability of distributed speculative LLM serving: Wasted Drafting Time and Verification Interference. To address these challenges, we propose WISP, an efficient and SLO-aware distributed LLM inference system that consists of an intelligent speculation controller, a verification time estimator, and a verification batch scheduler. These components collaboratively enhance drafting efficiency and optimize verification request scheduling on the server. Extensive numerical results show that WISP improves system capacity by up to 2.1x and 4.1x, and increases system goodput by up to 1.94x and 3.7x, compared to centralized serving and SLED, respectively.

cs.DC↗

arXiv2026

APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution by offloading KV cache management and parts of attention computation to the CPU. However, a key bottleneck remains: existing schedulers fail to effectively overlap CPU-offloaded tasks with GPU execution during the latency-critical, bandwidth-bound decode phase. This particularly penalizes real-time, decode-heavy applications (e.g., chat, Chain-of-Thought reasoning) which are currently underserved by existing systems, especially under memory pressure typical of edge or low-cost deployments. We present APEX, a novel, profiling-informed scheduling strategy that maximizes CPU-GPU parallelism during hybrid LLM inference. Unlike systems relying on static rules or purely heuristic approaches, APEX dynamically dispatches compute across heterogeneous resources by predicting execution times of CPU and GPU subtasks to maximize overlap while avoiding scheduling overheads. We evaluate APEX on diverse workloads and GPU architectures (NVIDIA T4, A10), using LLaMa-2-7B and LLaMa-3.1-8B models. Compared to GPU-only schedulers like vLLM, APEX improves throughput by 84% - 96% on T4 and 11% - 89% on A10 GPUs, while preserving latency. Against the best existing hybrid schedulers, it delivers up to 72% (T4) and 37% (A10) higher throughput in long-output settings. APEX significantly advances hybrid LLM inference efficiency on such memory-constrained hardware and provides a blueprint for scheduling in heterogeneous AI systems, filling a critical gap for efficient real-time LLM applications.

cs.DC↗

arXiv2026

Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level optimizations, lacking a holistic serving framework that addresses the unique memory dynamics of diffusion processes in production. We identify a critical "memory footprint crisis" specific to dLLMs, driven by monolithic logit tensors and the severe resource oscillation between compute-bound "Refresh" phases and bandwidth-bound "Reuse" phases. To bridge this gap, we present dLLM-Serve, an efficient dLLM serving system that co-optimizes memory footprint, computational scheduling, and generation quality. dLLM-Serve introduces Logit-Aware Activation Budgeting to decompose transient tensor peaks, a Phase-Multiplexed Scheduler to interleave heterogeneous request phases, and Head-Centric Sparse Attention to decouple logical sparsity from physical storage. We evaluate dLLM-Serve on diverse workloads (LiveBench, Burst, OSC) and GPUs (RTX 4090, L40S). Relative to the state-of-the-art baseline, dLLM-Serve improves throughput by 1.61$\times$-1.81$\times$ on the consumer-grade RTX 4090 and 1.60$\times$-1.74$\times$ on the server-grade NVIDIA L40S, while reducing tail latency by nearly 4$\times$ under heavy contention. dLLM-Serve establishes the first blueprint for scalable dLLM inference, converting theoretical algorithmic sparsity into tangible wall-clock acceleration across heterogeneous hardware. The code is available at https://github.com/chosen-ox/dLLM-Serve.

cs.DC↗

arXiv2025

SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware capabilities. Existing strategies, such as aggressive quantization, pruning, or remote inference, trade accuracy for efficiency or lead to substantial cost burdens. This position paper introduces a new framework that leverages speculative decoding, previously viewed primarily as a decoding acceleration technique for autoregressive generation of LLMs, as a promising approach specifically adapted for edge computing by orchestrating computation across heterogeneous devices. We propose \acronym, a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models, while a single, shared edge server verifies the tokens utilizing a more precise target model. To further increase the efficiency of verification, the edge server batch the diverse verification requests from devices. This approach supports device heterogeneity and reduces server-side memory footprint by sharing the same upstream target model across multiple devices. Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits: 2.2 more system throughput, 2.8 more system capacity, and better cost efficiency, all without sacrificing model accuracy.

cs.DC↗