arXiv AI
Aug 3
Topology-Aware Data Movement for Disaggregated GPU Inference
arXiv:2607. 28633v1 Announce Type: cross Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly.
DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
arXiv:2511. 04791v2 Announce Type: replace Abstract: Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive prefill and memory-bound decode phases.
Related stories
arXiv AI
Sep 15
mKernel: Fast Multi-GPU, Multi-Node Fused Kernels
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 AI
Jun 10
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
arXiv:2606. 10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads.
arXiv AI
Jul 23
Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts
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 AI
Jul 3
Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving
arXiv:2607. 02043v1 Announce Type: cross Abstract: Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering.
arXiv AI
Jul 7
Data Driven Optimization of GPU efficiency for Distributed LLM-Adapter Serving
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 Machine Learning
Sep 15
BOOST: Concurrent Access to Host Memory and HBM to Accelerate LLM Inference
arXiv:2609.13592v1 Announce Type: cross Abstract: GPU memory bandwidth and capacity limit throughput in large language model (LLM) inference. The GPU memory system consists of a primary tier of high-...
arXiv Machine Learning
Sep 23
Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures
The paper addresses the problem of non‑deterministic outputs from large language models (LLMs) when run on different GPU architectures, caused by floating‑point non‑associativity and hardware‑dependent kernel choices. It proposes a set of fixed‑configuration fused‑upcast GEMM kernels that load 16‑bit weights, upcast to FP32, and perform IEEE‑754 compliant reductions in a problem‑shape‑dependent order, ensuring identical linear‑layer outputs across NVIDIA Ampere, Ada, and Hopper GPUs. The new approach achieves 1.17–3.1× faster end‑to‑end performance than existing solutions and halves weight‑memory traffic while maintaining cross‑architecture reproducibility.
arXiv AI
Jun 24
CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation
arXiv:2606. 24506v1 Announce Type: cross Abstract: Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold.
arXiv AI
Jul 28
X-Stage: An Overlooked Pipeline Stage for Communication-Computation Overlap in DiT Inference
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.
arXiv AI
Aug 10
Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.
arXiv AI
Sep 24
EMA: Elastic and Performance Transparent Memory Across GPUs
arXiv:2609.27040v1 Announce Type: cross Abstract: Multi-GPU servers have become the standard building block of modern data centers, providing aggregated capacity through high-bandwidth interconnects....