arXiv subjects

Hanfei Yu

Publications and source records attributed to Hanfei Yu.

10 recordsLinked to original sources

arXiv2026

GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading

Serverless platforms increasingly host machine learning (ML) inference workflows, modeled as directed acyclic graphs (DAGs) of interdependent functions. Beyond container startup, each ML node must load libraries, model weights, and CUDA kernels before it can run. These costs accumulate along dependent DAG paths and place initialization on the end-to-end critical path. Existing systems optimize one half of this problem. DAG-agnostic pre-loading prepares nodes the request may never reach, wasting host and GPU memory. DAG-aware serving routes and scales whole functions, leaving the loading stages inside a node untouched. This paper presents GearUp, a serverless DAG inference serving system that removes ML-node loading from the end-to-end critical path at low resource cost. GearUp profiles the loading stages of each node and schedules them inside the slack time the DAG exposes, hiding initialization behind upstream execution. It reuses initialized instances within and across requests to avoid redundant cold starts. A probabilistic, traffic-adaptive keep-alive policy sets how long idle instances are retained, balancing memory cost against cold-start risk under bursty load. On the AMBER Alert and FINRA-ML workflows with NVIDIA L40S GPUs, GearUp reduces median end-to-end latency by 64.5% and 75.9% against SMIless, for median speedups of 3.1x and 10.0x over cold execution. Integrated GPU and host memory allocation fall by up to 83.9% and 94.6% against eager pre-loading in InstaInfer. GearUp achieves 4.2x strong scaling on four workers.

cs.DC↗

arXiv2026

Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries

Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and refining executable solutions from verifier feedback. Methods such as TTT-Discover use test-time training (TTT) to update the solution-generating LLM from verifier feedback, adapting its generation policy to improve subsequent proposals on the target problem. However, this becomes expensive when reliable execution requires a large model, since training must maintain gradients, optimizer states, and policy statistics while repeatedly generating long, structured outputs. It also complicates credit assignment: outcome-level verifier feedback must jointly evaluate the high-level strategy and its low-level implementation. In this work, we introduce Guidance-TTT, which separates these roles. A compact guidance model is trained at test time to propose high-level strategic changes, while a frozen execution model implements them as complete executable solutions. At each step, the system selects a promising previously discovered solution, proposes a change, executes and verifies it, and updates only the guidance model using an adaptive group-relative RL objective. This concentrates test-time learning on short strategic decisions while retaining the implementation capability of a substantially stronger model without adapting it. Without web access, Guidance-TTT produces strong solutions across four distinct domains: combinatorial optimization (Polyomino Packing), heuristic programming (AHC058), machine learning (Lasso), and GPU kernel optimization (TriMul). Across these tasks, it outperforms the best solutions reported in prior work while remaining competitive with state-of-the-art results on public online leaderboards. Code is available at https://github.com/Human-Agent-Society/reef/tree/guidance-ttt-support.

cs.AI↗

arXiv2026

MoEless: Efficient MoE LLM Serving with Serverless Experts

Large Language Models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale efficiently under stringent resource constraints. However, MoE's sparse activation causes severe expert load imbalance, where a few experts become stragglers while others remain underutilized, leading to inflated inference latency and cost. Existing solutions assume static, serverful model deployments, limiting expert elasticity and often incurring costly expert swapping or degraded output quality. We present MoEless, an efficient serverless MoE serving framework that mitigates expert load imbalance via elastic expert execution. MoEless leverages lightweight, layer-aware predictors to estimate incoming expert load distributions and proactively identify stragglers. We design optimized scaling and placement strategies to improve function locality, GPU utilization, and cross-expert load balance. MoEless is prototyped on top of Megatron-LM and deployed on an eight-GPU testbed. Experiments with open-source MoE models and real-world workloads show that MoEless reduces inference latency by 43% and inference cost by 84% compared to state-of-the-art solutions.

cs.DC↗

arXiv2026

ServerlessLoRA: Enabling Low-Latency Serverless Multi-LoRA Serving

Multi-LoRA (Low-Rank Adaptation) serving allows many specialized LLM variants to share the same base model by attaching lightweight adapters. This makes it attractive for serving large catalogs of domain-, tenant-, and task-specific models. However, existing deployments waste resources on rarely used adapters, while directly running LoRA inference on serverless platforms introduces high memory overhead, repeated cold starts, and poor scheduling decisions. This paper presents ServerlessLoRA, a serverless multi-LoRA serving system that separates serving state into shared backbone state, reusable variant warm state, and request-private state. ServerlessLoRA loads each backbone once, shares it read-only across isolated LoRA functions, batches selected backbone operations, selectively warms variant state, and routes requests based on state locality and GPU contention. Evaluated on industrial traces, ServerlessLoRA reduces time-to-first-token by up to 92.3% against serverless baselines and achieves 1.66-3.01 times and 2.20-3.26 times higher latency-cost efficiency than vLLM-LoRA and dLoRA, respectively.

cs.LG↗

arXiv2026

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that learns to act in them. Each is a stateful, multi-turn environment (state transitions, reward functions, and verification code), so one interface spans reasoning problems and multi-step agentic tool use. The Reasoning Agent's regret is estimated using the gap between its reward with and without privileged hints; in optimizing this regret signal the Environment Designer learns to target environments at the edge of the agent's capabilities while keeping them feasible. Through extensive experimentation, we find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory. Scaling to 30B-parameter models, SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks, and lifts the tool-use setting by +5.7 on BFCL-v4 multi-turn and +13.9 on ACEBench-Agent; on the games setting, the margin over the strongest baseline grows with model scale. By making environment design itself a learnable component, SPADE takes a concrete step toward open-ended self-improvement.

cs.CL↗

arXiv2026

The Diminishing Returns of Early-Exit Decoding in Modern LLMs

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining recipes and architectures that reduce layer redundancy, potentially limiting early-exit opportunities. We re-evaluate layer-wise early-exit in modern LLMs and analyze how intermediate representations evolve during training. We introduce a metric to quantify a model's intrinsic suitability for early-exit and propose a benchmark for researchers to explore the potential early-exit benefits on different models and workloads. Our results show a diminishing trend in early-exit effectiveness across newer model generations. We further find that dense transformers generally offer greater early-exit potential than Mixture-of-Experts and State Space Models. In addition, larger models, particularly those with more than 20 billion parameters, and base pretrained models without specialized tuning tend to exhibit higher early-exit potential.

cs.CL↗

arXiv2026

RLHFless: Serverless Computing for Efficient RLHF

Reinforcement Learning from Human Feedback (RLHF) has been widely applied to Large Language Model (LLM) post-training to align model outputs with human preferences. Recent models, such as DeepSeek-R1, have also shown RLHF's potential to improve LLM reasoning on complex tasks. In RL, inference and training co-exist, creating dynamic resource demands throughout the workflow. Compared to traditional RL, RLHF further challenges training efficiency due to expanding model sizes and resource consumption. Several RLHF frameworks aim to balance flexible abstraction and efficient execution. However, they rely on serverful infrastructures, which struggle with fine-grained resource variability. As a result, during synchronous RLHF training, idle time between or within RL components often causes overhead and resource wastage. To address these issues, we present RLHFless, the first scalable training framework for synchronous RLHF, built on serverless computing environments. RLHFless adapts to dynamic resource demands throughout the RLHF pipeline, pre-computes shared prefixes to avoid repeated computation, and uses a cost-aware actor scaling strategy that accounts for response length variation to find sweet spots with lower cost and higher speed. In addition, RLHFless assigns workloads efficiently to reduce intra-function imbalance and idle time. Experiments on both physical testbeds and a large-scale simulated cluster show that RLHFless achieves up to 1.35x speedup and 44.8% cost reduction compared to the state-of-the-art baseline.

cs.AI↗

arXiv2025

Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE) architecture has become a popular backbone for modern LLMs. However, despite the benefits, serving MoE-based LLMs experience severe memory inefficiency due to sparsely activated experts. Recent studies propose to offload inactive experts from GPU memory to CPU memory to improve the serving efficiency of MoE models. However, they either incur high inference latency or high model memory footprints due to coarse-grained designs. To tame the latency-memory trade-off in MoE serving, we present FineMoE, a fine-grained expert offloading system for MoE serving that achieves low inference latency with memory efficiency. We design FineMoE to extract fine-grained expert selection patterns from MoE models and semantic hints from input prompts to efficiently guide expert prefetching, caching, and offloading decisions. FineMoE is prototyped on top of HuggingFace Transformers and deployed on a six-GPU testbed. Experiments with open-source MoE models and real-world workloads show that FineMoE reduces inference latency by 47% and improves expert hit rate by 39% over state-of-the-art solutions.

cs.LG↗

arXiv2022

Accelerating Serverless Computing by Harvesting Idle Resources

Serverless computing automates fine-grained resource scaling and simplifies the development and deployment of online services with stateless functions. However, it is still non-trivial for users to allocate appropriate resources due to various function types, dependencies, and input sizes. Misconfiguration of resource allocations leaves functions either under-provisioned or over-provisioned and leads to continuous low resource utilization. This paper presents Freyr, a new resource manager (RM) for serverless platforms that maximizes resource efficiency by dynamically harvesting idle resources from over-provisioned functions to under-provisioned functions. Freyr monitors each function's resource utilization in real-time, detects over-provisioning and under-provisioning, and learns to harvest idle resources safely and accelerates functions efficiently by applying deep reinforcement learning algorithms along with a safeguard mechanism. We have implemented and deployed a Freyr prototype in a 13-node Apache OpenWhisk cluster. Experimental results show that 38.8% of function invocations have idle resources harvested by Freyr, and 39.2% of invocations are accelerated by the harvested resources. Freyr reduces the 99th-percentile function response latency by 32.1% compared to the baseline RMs.

cs.DC↗

arXiv2020

Leveraging GPT-2 for Classifying Spam Reviews with Limited Labeled Data via Adversarial Training

Online reviews are a vital source of information when purchasing a service or a product. Opinion spammers manipulate these reviews, deliberately altering the overall perception of the service. Though there exists a corpus of online reviews, only a few have been labeled as spam or non-spam, making it difficult to train spam detection models. We propose an adversarial training mechanism leveraging the capabilities of Generative Pre-Training 2 (GPT-2) for classifying opinion spam with limited labeled data and a large set of unlabeled data. Experiments on TripAdvisor and YelpZip datasets show that the proposed model outperforms state-of-the-art techniques by at least 7% in terms of accuracy when labeled data is limited. The proposed model can also generate synthetic spam/non-spam reviews with reasonable perplexity, thereby, providing additional labeled data during training.

cs.AI↗