arXiv subjects

Ruoyu Qin

Publications and source records attributed to Ruoyu Qin.

7 recordsLinked to original sources

arXiv2026

Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter

Prefill-decode (PD) disaggregation has become the standard architecture for large-scale LLM serving, but in practice its deployment boundary is still determined by KVCache transfer. In conventional dense-attention models, prefill generates huge KVCache traffics that keep prefill and decode tightly coupled within a single high-bandwidth network domain, limiting heterogeneous deployment and resource elasticity. Recent hybrid-attention architectures substantially reduce KVCache size, making cross-cluster KVCache transport increasingly plausible. However, smaller KVCache alone does not make heterogeneous cross-datacenter PD serving practical: real workloads remain bursty, request lengths are highly skewed, prefix caches are unevenly distributed, and inter-cluster bandwidth fluctuates. A naive design that fully externalizes prefill can therefore still suffer from congestion, unstable queueing, and poor utilization. We present Prefill-as-a-Service (PrfaaS), a cross-datacenter serving architecture that selectively offloads long-context prefill to standalone, compute-dense prefill clusters and transfers the resulting KVCache over commodity Ethernet to local PD clusters for decode. Rather than treating reduced KVCache as sufficient, PrfaaS combines model-side KV efficiency with system-side selective offloading, bandwidth-aware scheduling, and cache-aware request placement. This design removes the requirement that heterogeneous accelerators share the same low-latency RDMA fabric, enabling independent scaling of prefill and decode capacity across loosely coupled clusters. In a case study using an internal 1T-parameter hybrid model, a PrfaaS-augmented heterogeneous deployment achieves 54% higher serving throughput and 64% lower P90 TTFT than a homogeneous PD baseline, with approximately 15% throughput gain at equal cost, while consuming only modest cross-datacenter bandwidth.

cs.DC↗

arXiv2026

TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving

Modern GPU clusters rely on complex, heterogeneous interconnects. As large language model (LLM) serving shifts toward agentic reasoning, KVCache becomes a first-class mobile asset, driving frequent migrations and massive elephant flows that dominate the execution critical path. Operating Mooncake Transfer Engine (TE) on thousands of GPUs exposed a fundamental flaw in existing frameworks: imperative, early-binding path selection. This rigidity results in state-blind striping that ignores congestion and grey failures, leading to bandwidth stranding. This also produces operational fragility where routine faults require manual intervention. We present TENT, a declarative orchestration engine that decouples transfer intent from physical execution. By abstracting interconnects into a unified resource pool, TENT shifts path resolution from initialization to slice-time late binding. Applications simply declare transfer intents, while TENT dynamically "sprays" fine-grained slices across rails based on real-time telemetry and predictive cost modeling. This orchestration eliminates head-of-line (HoL) blocking and enables transparent, sub-50 ms self-healing by rerouting slices around failures or degradations without application-level intervention. TENT serves as the production data plane for LLM inference and reinforcement learning (RL) pipelines at multiple industrial clusters. Our evaluation shows that TE+ outperforms state-of-the-art baselines, including Mooncake TE, NIXL, and UCCL. In LLM inference with SGLang HiCache, TE+ achieves up to 1.36x higher throughput and 26% lower P90 time-to-first-token (TTFT) than Mooncake TE. In RL pipelines, TENT accelerates parameter updates in Moonshot Checkpoint Engine by 20-26%.

cs.DC↗

arXiv2025

Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning

Reinforcement Learning (RL) has emerged as a critical technique for advancing modern Large Language Models (LLMs), yet existing synchronous RL systems face severe performance bottlenecks. The rollout phase, which dominates end-to-end iteration time, suffers from substantial long-tail latency and poor resource utilization due to inherent workload imbalance. We present Seer, a novel context learning RL system that addresses these challenges through a key observation: requests sharing the same prompt exhibit strong similarities in output lengths and response patterns. Leveraging this insight, Seer introduces three coordinated techniques: (1) divided rollout for dynamic load balancing, (2) context-aware scheduling to mitigate long-tail request delays, and (3) adaptive grouped speculative decoding to accelerate generation. These mechanisms work in concert to markedly reduce long-tail latency and improve resource efficiency during rollout. Evaluations on production-grade RL workloads demonstrate that Seer achieves up to 2.04$\times$ end-to-end rollout throughput improvement compared to the state-of-the-art synchronous RL systems, while notably reducing long-tail latency by 72-94%.

cs.DC↗

arXiv2025

Kimi K2: Open Agentic Intelligence

We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which improves upon Muon with a novel QK-clip technique to address training instability while enjoying the advanced token efficiency of Muon. Based on MuonClip, K2 was pre-trained on 15.5 trillion tokens with zero loss spike. During post-training, K2 undergoes a multi-stage post-training process, highlighted by a large-scale agentic data synthesis pipeline and a joint reinforcement learning (RL) stage, where the model improves its capabilities through interactions with real and synthetic environments. Kimi K2 achieves state-of-the-art performance among open-source non-thinking models, with strengths in agentic capabilities. Notably, K2 obtains 66.1 on Tau2-Bench, 76.5 on ACEBench (En), 65.8 on SWE-Bench Verified, and 47.3 on SWE-Bench Multilingual -- surpassing most open and closed-sourced baselines in non-thinking settings. It also exhibits strong capabilities in coding, mathematics, and reasoning tasks, with a score of 53.7 on LiveCodeBench v6, 49.5 on AIME 2025, 75.1 on GPQA-Diamond, and 27.1 on OJBench, all without extended thinking. These results position Kimi K2 as one of the most capable open-source large language models to date, particularly in software engineering and agentic tasks. We release our base and post-trained model checkpoints to facilitate future research and applications of agentic intelligence.

cs.LG↗

arXiv2024

TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise

Large Language Models (LLMs) exhibit impressive reasoning and data augmentation capabilities in various NLP tasks. However, what about small models? In this work, we propose TeacherLM-7.1B, capable of annotating relevant fundamentals, chain of thought, and common mistakes for most NLP samples, which makes annotation more than just an answer, thus allowing other models to learn "why" instead of just "what". The TeacherLM-7.1B model achieved a zero-shot score of 52.3 on MMLU, surpassing most models with over 100B parameters. Even more remarkable is its data augmentation ability. Based on TeacherLM-7.1B, we augmented 58 NLP datasets and taught various student models with different parameters from OPT and BLOOM series in a multi-task setting. The experimental results indicate that the data augmentation provided by TeacherLM has brought significant benefits. We will release the TeacherLM series of models and augmented datasets as open-source.

cs.CL↗

arXiv2024

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and decoding clusters. It also leverages the underutilized CPU, DRAM, and SSD resources of the GPU cluster to implement a disaggregated cache of KVCache. The core of Mooncake is its KVCache-centric scheduler, which balances maximizing overall effective throughput while meeting latency-related Service Level Objectives (SLOs). Unlike traditional studies that assume all requests will be processed, Mooncake faces challenges due to highly overloaded scenarios. To mitigate these, we developed a prediction-based early rejection policy. Experiments show that Mooncake excels in long-context scenarios. Compared to the baseline method, Mooncake can achieve up to a 525% increase in throughput in certain simulated scenarios while adhering to SLOs. Under real workloads, Mooncake's innovative architecture enables Kimi to handle 75% more requests.

cs.DC↗

arXiv2023

Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment. In this paper, we propose Position-enhanced Visual Instruction Tuning (PVIT), which extends the functionality of MLLMs by integrating an additional region-level vision encoder. This integration promotes a more detailed comprehension of images for the MLLM. In addition, to efficiently achieve a fine-grained alignment between the vision modules and the LLM, we design multiple data generation strategies to construct an image-region-language instruction dataset. Finally, we present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model. Code and data will be released at https://github.com/PVIT-official/PVIT.

cs.CV↗