arXiv:2512. 10236v2 Announce Type: replace-cross Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs.
arXiv:2607. 19539v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block for scaling large language models (LLMs) to trillion-parameter regimes.
arXiv:2605.21603v1 Announce Type: cross Abstract: Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different r...
arXiv:2607. 02630v1 Announce Type: cross Abstract: Hardware accelerators now sit on the critical path of online serving.
arXiv:2607. 28633v1 Announce Type: cross Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly.
arXiv:2509. 23722v2 Announce Type: replace-cross Abstract: Pipeline parallelism is widely used to train large language models (LLMs).
arXiv:2609.13585v1 Announce Type: cross Abstract: Communication has become a bottleneck in distributed training and inference of large models. Overlapping communication with computation at the granul...
arXiv:2602. 24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.
arXiv:2607. 23264v1 Announce Type: cross Abstract: Fine-grained, device-initiated communication lets persistent GPU kernels in distributed diffusion transformer (DiT) inference issue remote stores and overlap data movement with Tensor Core computation.
Scepsy is a serving system designed to efficiently schedule arbitrary multi‑LLM agentic workflows on GPU clusters. It leverages the observation that each LLM’s share of execution time remains relatively stable across requests, profiling LLMs under various parallelism levels to build an Aggregate LLM Pipeline that predicts throughput and latency. Using this predictor, Scepsy searches for optimal GPU allocations—balancing fractional GPU shares, tensor parallelism, and replica counts—and then heuristically places them on the cluster to reduce fragmentation and honor network topology, achieving up to 2.5× higher throughput and 1.0–3.3× lower latency compared to baseline approaches.
arXiv:2511. 15503v3 Announce Type: replace-cross Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory bandwidth available at PIM cores.
The paper presents a method for distributing large language model inference across multiple Intel AI PCs by splitting the model into pipeline shards, each pre‑compiled into an OpenVINO graph. Three key techniques—beam_idx Gather to enable GPU optimizations, speculative decoding on stateful models, and interleaved micro‑batching—allow a two‑node Llama 3.1 8B INT4 pipeline to serve two users at 1.79× the throughput of a single‑node model, while a four‑node deployment can run a 70B model that no single PC can hold. The authors provide code, benchmark logs, and reproduction scripts on GitHub.
arXiv:2608. 16336v1 Announce Type: cross Abstract: Modern LLM serving deployments must simultaneously satisfy heterogeneous service-level objectives (SLOs) across a diverse population of user tiers, ranging from latency-critical API calls to background batch processing.