Decoupled I/O-Dominant Pipelines for Large-Scale Whole-Slide Image Embedding Extraction

Whole-slide images (WSIs) are central to computational pathology but are prohibitively large, making patch-based processing the practical unit for foundation model inference. At scale, however, generating and handling massive numbers of patches on quickly introduces significant I/O and orchestration overhead, often dominating end-to-end performance. We present a decoupled, I/O-aware pipeline for large-scale WSI embedding extraction that decomposes the workflow into three stages: (1) patch generation and staging, (2) embarrassingly parallel embedding inference, and (3) sharded vector database ingestion. This design isolates data movement from compute, enabling efficient patch delivery, scalable multi-node inference with minimal communication. The resulting system produces a distributed vector database where embeddings are persistently coupled with rich metadata (e.g., patient, slide, and patch attributes), enabling efficient filtering, retrieval, and downstream reuse. This representation database is compact and reusable for tasks such as retrieval, classification, and few-shot learning, particularly benefiting low-resource environments. We show that decoupling I/O, computation, and ingestion enables high-throughput WSI embedding extraction at scale. By characterizing the scaling envelope, we demonstrate that storage dominates beyond moderate concurrency, reframing WSI embedding extraction as a data-centric systems problem rather than a purely compute-bound workload.

TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modeling

Training high-resolution AI-based Earth forecasting models is memory-intensive. Window-based Swin Transformers reduce the quadratic cost of global attention, but existing distributed systems such as AERIS primarily target pixel-level models and do not jointly support convolutional sampling modules and shifted-window execution. Long-lead rollout finetuning further increases activation memory. To address these challenges, we present TERRA, a hierarchical parallel training framework for high-resolution Earth forecasting. TERRA introduces Sampling-Aware Window, Sequence, and Tensor Parallelism (SAWSTP), which preserves spatially contiguous layouts for sampling modules and routes tokens into topology-aware ragged window layouts for Transformer execution. For long-lead finetuning, Memory Orchestration (MO) provides rollout-aware checkpoint planning and combines input buffering with budget-constrained activation offloading. Experiments on the $1/12^\circ$ GLORYS-based Wenhai workload show that TERRA supports models with up to 11.4B parameters on 96 H200 GPUs and sustains up to $39.76$ PFLOPS, achieving $65.0\%$ strong-scaling and $94.1\%$ weak-scaling efficiency. Compared with checkpoint-only policies, MO further reduces peak allocated GPU memory by $32.2\%$--$51.8\%$ with at most $20.0\%$ step-time overhead, which makes finetuning with smaller patch sizes and longer rollouts feasible for improved forecasting accuracy.

TrimMoE A communication aware and adaptive depth framework for distributed edge inference

Serving Mixture-of-Experts (MoE) large language models across distributed edge servers is bottlenecked by the cross-server expert transmission. The existing approaches mainly focus on how to reach a remote expert faster. However, in this paper, we instead consider whether a given layer, and the layers after it, need to be executed at all. To this end, a communication-aware adaptive-depth framework is proposed in this paper, termed TrimMoE, which couples layer skipping and confidence-based early exit with substitute execution and server-expert selection under a unified quality budget. Specifically, in the offline stage, TrimMoE freezes the backbone, trains the lightweight per-layer exit heads, calibrates the per-layer importance thresholds, and allocates the expert replicas by a skip/exit-aware redundancy benefit. In the online stage, a transition-aware look-ahead anticipates the token movement, so that the depth reduction targets the costliest transmissions, and besides, two feedback rules adapt the delay-quality weights and the exit threshold. Moreover, we prove that the substitution-and-skipping proxy degradation never exceeds the configured budget, and that the early exit is admitted only under a calibrated confidence gate. On a heterogeneous 10-server testbed with Switch-Base-8E, Qwen-MoE-A2.7B, and Mixtral-8x7B, TrimMoE reduces the average latency by up to 62.8%, lowers the cross-server traffic and the remote-execution ratio, and sustains high throughput under load, while keeping the task-quality degradation within a 2% bound.

Clustered Edge Intelligence: Beyond Just Convergence of Edge Computing and AI

We are moving from an information age to the age of intelligence. A decade, or possibly less than that, data will not be the gold anymore rather the derived intelligence out of the data and the information we posses from the edge of the network. Existing Edge Intelligence research focuses mainly on two directions: using AI for edge resource management and deploying lightweight AI models on edge devices. However, existing edge computing research lacks an intelligence-centric framework in which derived intelligence is treated as a first-class, independently manageable entity that can be described, discovered, observed, shared, reused, and dynamically clustered across heterogeneous edge devices and applications. To address these research gaps, we introduced Clustered Edge Intelligence, a visionary intelligence-centric approach. The aim of CEI is to make intelligence a shareable and reusable first-class entity that can be independently represented, discovered, observed, exchanged, and managed across the distributed edge-cloud continuum. We present a three layer CEI architecture and examine enabling technologies and research dimensions, including intelligence inventories, semantic knowledge representation, communication, discoverability, observability, lifecycle automation, clustering mechanisms, marketplaces, interoperability, and standardization.

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving

The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor. This survey classifies more than thirty KV-management systems and frameworks using four axes: locality, lifetime, ownership, and substrate. The axes reveal five architectural archetypes -- local-paged, disaggregated-pipeline, shared-store, memory-pool, and hybrid-tier. Once workload and hardware are fixed, ownership accounts for much of the remaining design variance among distributed systems. The survey also audits current evaluations and identifies seven missing KV-specific measurements, linking them to open problems in fault tolerance, isolation, tiered eviction, speculative decoding, MoE serving, and shared-cache semantics.

Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning

Federated Learning often suffers under non-independently and identically distributed data, where a single global model may fail to represent the diversity of client distributions. Clustered Federated Learning mitigates this issue by training specialized models for groups of similar clients, but existing approaches often couple cluster assignment with the main training loop, increasing computational and communication costs. We propose a lightweight clustering approach based on Random Network Distillation. Each client trains a compact Random Network Distillation predictor on its local data and uses its prediction error as a novelty signal to estimate similarity with other clients. This enables the discovery of meaningful client groups before federated training, without sharing raw data or repeatedly evaluating the main model. Crucially, the resulting federations emerge from local novelty estimates at runtime, making the method suitable for autonomous large-scale distributed systems where neither the number of clusters nor the collaboration structure can be specified a priori. Overall, by decoupling clustering from learning, the method provides a task-agnostic and efficient mechanism for autonomous collaboration under non-independently and identically distributed data.

BatchGen: An Architecture for Scalable and Efficient Batch Inference

Batch inference has become a central mode of AI computation, yet existing inference engines still rely on execution models designed for interactive serving. When scaled to millions of sequences, batch workloads reveal two fundamental requirements: the ability to handle extreme inter- and intra-sequence load variation that emerges only at runtime, and the ability to sustain high utilization across large fleets of GPUs. Existing systems fail to meet these requirements, losing substantial fractions of achievable throughput. We introduce a new architectural foundation for batch inference: the sequence coroutine compute model, which represents each sequence as a fine-grained, event-driven coroutine. This model exposes expressive primitives that allow the runtime to reorganize work dynamically, enabling larger expert-level batches, mitigating stragglers, reallocating work across devices, and maintaining utilization even on cost-effective or memory-constrained GPUs. Building on this abstraction, we implement BatchGen, a production-ready system that uses the coroutine model at cluster scale. On a 128-GPU cluster, BatchGen reduces batch completion time by up to $2.3\times$, and on memory-constrained accelerators it outperforms the strongest offloading baseline by up to $9.6\times$. We will open-source BatchGen at https://github.com/batchgen-project/batchgen