expert-parallelism

Tag

Cards List
#expert-parallelism

The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert Parallelism

arXiv cs.CL · 2026-08-11 Cached

A technical survey of Mixture-of-Experts architectures in LLMs, organizing evolution along expert granularity, topology, routing, load balancing, and execution, and proposing complementary views of architectural milestones and control planes.

0 favorites 0 likes
#expert-parallelism

EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference

arXiv cs.LG · 2026-08-11 Cached

This paper presents EasyBalance, a cross-layer load balancing strategy for distributed Mixture-of-Experts (MoE) inference that schedules and jointly executes workloads from different layers to mitigate GPU idling without modifying expert-device mappings, reducing idle time by over 40% in experiments.

0 favorites 0 likes
#expert-parallelism

Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement

arXiv cs.LG · 2026-07-13 Cached

This paper introduces Director, a distributed MoE serving system that minimizes end-to-end latency using prediction-driven, online proactive expert placement. It employs a lightweight predictor and a relaxation-based optimizer to achieve up to 55% latency reduction for models like Mistral, DeepSeek, and Qwen.

0 favorites 0 likes
#expert-parallelism

@h100envy: Ex-Berkeley PhD who leads SGLang at xAI explained how they serve Grok on 100K GPUs in 23 minutes - better than $2000 in…

X AI KOLs Timeline · 2026-07-06 Cached

A former Berkeley PhD who leads SGLang at xAI explains how they serve Grok on 100K GPUs using split prefill/decode, expert sharding, and communication/computation overlap to achieve DeepSeek-API-killing prices.

0 favorites 0 likes
#expert-parallelism

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference

arXiv cs.LG · 2026-05-08 Cached

MACS is a training-free inference framework that mitigates the straggler effect in expert parallelism for multimodal MoE MLLMs by introducing entropy-weighted load and dynamic modality-adaptive capacity mechanisms.

0 favorites 0 likes
#expert-parallelism

Federation of Experts: Communication Efficient Distributed Inference for Large Language Models

Hugging Face Daily Papers · 2026-05-07 Cached

Federation of Experts (FoE) restructures mixture-of-experts blocks into clusters that process KV heads independently, eliminating inter-node communication bottlenecks and improving inference throughput and latency by up to 5.2x while maintaining generation quality.

0 favorites 0 likes
← Back to home

Submit Feedback