Yongwei Wu

Ao Zhang, Yunwen Liu, Ren Zhang et al.

This study investigates the rapid centralization of the Ethereum builder market under the Proposer-Builder Separation (PBS) architecture. We argue that existing research, by focusing predominantly on influential order flows, lacks a comprehensive evaluation of order flow behavioral patterns and economic purposes. To address this gap, we analyze Ethereum transactions from September 2023 to August 2025 to characterize Exclusive Order Flows (EOFs) and non-atomic Maximal Extractable Value (MEV) -- the missing components corresponding to these behavioral and economic dimensions, respectively. We introduce a novel exclusivity metric based on Kullback-Leibler divergence and employ supervised learning to identify 75 EOFs and 322 non-atomic MEV flows, which account for 71\% and 23\% of trading-related builder revenue. A longitudinal analysis of builder strategies across these dimensions delineates the market's evolution into four distinct eras, revealing that while EOFs were instrumental in establishing early dominance, incumbents have since decoupled market share from immediate EOF dependency by leveraging entrenched network effects. Ultimately, we conclude that builder centralization is an emergent property of the PBS framework itself, as the architecture systematically violates the fundamental prerequisites of a competitive market.

Ruoyu Qin, Weiran He, Yaoyu Wang et al.

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% and 32% higher serving throughput than homogeneous PD and naive heterogeneous baselines, respectively, while consuming only modest cross-datacenter bandwidth.

Feng Ren, Ruoyu Qin, Teng Ma et al.

Modern GPU clusters are built upon a complex hierarchy of heterogeneous interconnects, ranging from multi-rail RDMA to proprietary fabrics such as Multi-Node NVLink and Ascend UB. Orchestrating these diverse links effectively remains a critical challenge in disaggregated LLM serving. Operating Mooncake TE on thousands of GPUs exposed a critical limitation shared by existing frameworks: imperative, statically bound path selection. This rigidity forces engines to rely on state-blind striping that ignores congestion signals, creating communication silos, wasting multi-rail bandwidth due to head-of-line blocking, and leading to operational fragility where routine faults require manual intervention. We present TENT, a data-movement engine that decouples transfer intent from physical execution. Instead of locking workloads to fixed backends, TENT unifies heterogeneous interconnects into a single dynamic resource pool. Applications simply declare transfer intents, while TENT dynamically decomposes elephant flows into fine-grained slices and "sprays" them across links based on instantaneous link quality. This telemetry-driven orchestration eliminates head-of-line blocking and enables transparent, sub-50 ms self-healing by rerouting slices around failures without application logic. TENT serves as the production data plane for LLM inference and RL pipelines at multiple industrial sites. Our evaluation on H800 HGX clusters shows that TENT outperforms state-of-the-art baselines, including Mooncake TE, NIXL, and UCCL. In LLM inference with SGLang HiCache, TENT achieves up to 1.36x higher throughput and 26% lower P90 TTFT than Mooncake TE. In RL pipelines, TENT accelerates parameter updates in Moonshot Checkpoint Engine by 20-26%.

Jialiang Huang, Teng Ma, Zheng Liu et al.

Serverless computing is renowned for its computation elasticity, yet its full potential is often constrained by the requirement for functions to operate within local and dedicated background environments, resulting in limited memory elasticity. To address this limitation, this paper introduces TrEnv-X, a co-designed integration of the serverless platform with the operating system and CXL/RDMA-based remote memory pools. TrEnv-X's core innovations are repurposable sandboxes, which can be shared across different functions to decrease the associated creation overhead, and OS-level memory templates, which enable rapid state restoration from CXL/RDMA-based remote memory pools. To further demonstrate TrEnv-X's versatility, we generalize its design from traditional containers for microVM-based agent workloads and introduce new optimizations, including browser sharing and a page cache bypassing mechanism. Our evaluation shows that TrEnv-X achieves up to 7x reduction in P99 latency and 48% memory savings for container-based functions. When applied to LLM agents, it reduces the P99 latency by up to 58% and memory usage by 61% compared to state-of-the-art systems like E2B.

Xun Sun, Shaoyuan Chen, Pingchuan Ma et al.

Mixture-of-Experts (MoE) serving relies on wide expert parallelism (EP) to aggregate the memory capacity and bandwidth of many GPUs within one inference instance. This efficiency comes with a systems cost: every decoding step depends on token dispatch and combination across all active EP ranks, so even one rank failure can disrupt the entire service. Existing EP stacks handle such failures poorly because they treat membership as a fixed configuration established at initialization. The same rank set determines communicator state, expert placement, and the routing metadata baked into CUDA execution graphs, leaving the system with no way to shrink around a failure while keeping the instance valid. This paper argues that partial-failure tolerance should instead be formulated as a live EP validity problem. We present EEP, a communication and runtime substrate that represents membership as explicit, mutable runtime state. EEP repairs the specific state invalidated by a fault: it restores peer reachability without rebuilding the communication substrate, repairs lost expert coverage through a bandwidth-aware hierarchy, and reintegrates repaired ranks without forcing healthy ranks to recapture their CUDA graphs. We implement EEP in an EP serving stack integrated with SGLang and evaluate it under steady-state serving, failure recovery, and rank reintegration. The results show that explicit mutable membership preserves the steady-state fast path, staying within 4.4% of a fixed-membership DeepEP baseline under static serving, while turning a local rank fault from whole-instance downtime into two bounded interruptions. On a single-rank failure workload, EEP incurs an 11s recovery pause and an 8s reintegration pause, and restores throughput to within 95% of the pre-fault level within 52s, whereas a fixed-membership full-restart baseline remains unavailable until 348s.

Shaoyuan Chen, Wencong Xiao, Yutong Lin et al.

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators. Although disaggregated serving architectures have been proposed to split different phases of LLM inference, the efficiency of decoding phase is still low. This is caused by the varying resource demands of different operators in the transformer-based LLMs. Specifically, the attention operator is memory-intensive, exhibiting a memory access pattern that clashes with the strengths of modern accelerators, especially for long context requests. To enhance the efficiency of LLM decoding, we introduce model-attention disaggregation. This approach leverages a collection of cheap, memory-optimized devices for the attention operator while still utilizing high-end accelerators for other parts of the model. This heterogeneous setup ensures that each component is tailored to its specific workload, maximizing overall performance and cost efficiency. Our comprehensive analysis and experiments confirm the viability of splitting the attention computation over multiple devices. Also, the communication bandwidth required between heterogeneous devices proves to be manageable with prevalent networking technologies. To further validate our theory, we develop and deploy Lamina, an LLM inference system that incorporates model-attention disaggregation in a distributed heterogeneous cluster. Experimental results indicate that Lamina can provide 16.1 ~ 90.1% higher estimated throughput than existing solutions with similar costs.

Jiahao Wang, Weiyu Xie, Mingxing Zhang et al.

Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token (TTFT). To mitigate this issue, existing solutions aim to reuse the preprocessed KV cache of each retrieved chunk to accelerate RAG. However, the lack of cross-chunk contextual information leads to a significant drop in generation quality, leaving the potential benefits of KV cache reuse largely unfulfilled. The challenge lies in how to reuse the precomputed KV cache of chunks while preserving generation quality. We propose FusionRAG, a novel inference framework that optimizes both the preprocessing and reprocessing stages of RAG. In the offline preprocessing stage, we embed information from other related text chunks into each chunk, while in the online reprocessing stage, we recompute the KV cache for tokens that the model focuses on. As a result, we achieve a better trade-off between generation quality and efficiency. According to our experiments, FusionRAG significantly improves generation quality at the same recomputation ratio compared to previous state-of-the-art solutions. By recomputing fewer than 15% of the tokens, FusionRAG achieves up to 70% higher normalized F1 scores than baselines and reduces TTFT by 2.66x-9.39x compared to Full Attention.

Ruoyu Qin, Weiran He, Weixiao Huang et al.

Reinforcement Learning (RL) has become critical 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 online context learning system that addresses these challenges by exploiting previously overlooked similarities in output lengths and generation patterns among requests sharing the same prompt. Seer introduces three key techniques: divided rollout for dynamic load balancing, context-aware scheduling, and adaptive grouped speculative decoding. Together, these mechanisms substantially reduce long-tail latency and improve resource efficiency during rollout. Evaluations on production-grade RL workloads demonstrate that Seer improves end-to-end rollout throughput by 74% to 97% and reduces long-tail latency by 75% to 93% compared to state-of-the-art synchronous RL systems, significantly accelerating RL training iterations.

Enda Yu, Zhaoning Zhang, Dezun Dong et al.

Mixture-of-Experts (MoE) models face memory and PCIe latency bottlenecks when deployed on commodity hardware. Offloading expert weights to CPU memory results in PCIe transfer latency that exceeds GPU computation by several folds. We present PreScope, a prediction-driven expert scheduling system that addresses three key challenges: inaccurate activation prediction, PCIe bandwidth competition, and cross-device scheduling complexity. Our solution includes: 1) Learnable Layer-Aware Predictor (LLaPor) that captures layer-specific expert activation patterns; 2) Prefetch-Aware Cross-Layer Scheduling (PreSched) that generates globally optimal plans balancing prefetching costs and loading overhead; 3) Asynchronous I/O Optimizer (AsyncIO) that decouples I/O from computation, eliminating waiting bubbles. PreScope achieves 141% higher throughput and 74.6% lower latency than state-of-the-art solutions.

Ruoyu Qin, Zheming Li, Weiran He et al.

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.