REVIEW 19 cited by
MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache
read the original abstract
This paper presents MoE-Infinity, an efficient MoE inference system designed for personal machines with limited GPU memory capacity. The key idea for MoE-Infinity is that on personal machines, which are often single-user environments, MoE-based LLMs typically operate with a batch size of one. In this setting, MoE models exhibit a high degree of activation sparsity, meaning a small number of experts are frequently reused in generating tokens during the decode phase. Leveraging this idea, we design a sparsity-aware expert cache, which can trace the sparse activation of experts during inference and carefully select the trace that represents the sparsity pattern. By analyzing these selected traces, MoE-Infinity guides the replacement and prefetching of the expert cache, providing 3.1-16.7x per-token latency improvements over numerous state-of-the-art systems, including vLLM, Ollama, DeepSpeed and BrainStorm across various MoE models (DeepSeek and Mixtral) when handling different LLM tasks. MoE-Infinity's source code is publicly available at https://github.com/EfficientMoE/MoE-Infinity
Forward citations
Cited by 19 Pith papers
-
DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance
DuoServe-MoE decouples prefill and decode phases in MoE LLM inference with a two-stream CUDA pipeline for prefill and an offline-trained predictor for decode, reporting up to 5.34x TTFT and 7.55x end-to-end latency gains.
-
Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study
On bandwidth-bound edge hardware, MoE inference cost tracks total parameters rather than active ones, so sparse activation fails to deliver the expected throughput or energy gains.
-
DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference
Fixed-footprint shared+top-1+draft-expert self-speculation with residual/router distillation, expansion-aware truncation, and prefetch raises end-device MoE decode throughput ~1.45× while keeping exact target outputs.
-
Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices
Tensor-granularity hybrid CPU-GPU offloading with static placement plus load-aware dynamic transfer yields up to 1.94× prefill and 3.29× decode throughput for local LLMs on consumer devices.
-
WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware
WiSP achieves up to 1.95x decode throughput on low-resource MoE serving by dynamically paging reused experts and using MV-WSA to allocate VRAM between experts and KV cache, with the offline policy performing well on b...
-
C2CServe: Leveraging NVLink-C2C for Elastic Serverless LLM Serving on MIG
C2CServe is a request-granularity serverless LLM serving system that keeps weights in host memory and streams them via C2C to MIG instances, cutting cold-start latency up to 7.1x while preserving TTFT/TPOT under contention.
-
VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading
VisMMoE exploits visual-expert affinity via token pruning to achieve up to 2.68x faster VL-MoE inference on memory-constrained hardware while keeping accuracy competitive.
-
Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs
NPUMoE accelerates MoE LLM inference on Apple Silicon NPUs via offline-calibrated static expert tiers, grouped execution, and load-aware graph residency, delivering 1.32x-5.55x lower latency and 1.81x-7.37x better ene...
-
Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy
In shared-prefix MoE code generation, routing Jaccard similarity reaches 0.649 for identical tokens and 0.175 for different tokens, with layer-wise crossing patterns, and 67% of compiled codes fall into three assembly...
-
ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving
ELMoE-3D achieves 6.6x average speedup and 4.4x energy efficiency gain for MoE serving on 3D hardware by scaling expert and bit elasticity for elastic self-speculative decoding.
-
FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
FluxMoE decouples MoE expert weights from persistent GPU residency via on-demand paging, achieving up to 3x throughput gains over vLLM in memory-constrained inference without accuracy loss.
-
Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices
Tensor-granularity hybrid CPU-GPU offloading with static placement and load-aware dynamic transfer improves local LLM prefill and decode throughput on consumer devices.
-
BatchGen: An Architecture for Scalable and Efficient Batch Inference
BatchGen uses a coroutine-based model to dynamically reorganize inference work across GPUs, achieving up to 2.3x faster batch completion on 128 GPUs and 9.6x improvement on memory-constrained hardware.
-
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload
TIDE schedules I/O-aware expert offloading for MoE diffusion LLMs by solving for an optimal refresh interval that exploits temporal stability of activations, yielding up to 1.5x throughput gain losslessly.
-
CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution
CoX-MoE achieves up to 7.1x higher throughput than FlexGen for MoE inference via coalesced expert execution and AMX-enabled CPU-GPU orchestration with static expert stratification.
-
ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
ZipMoE delivers up to 72.77% lower inference latency and 6.76x higher throughput for on-device MoE models via lossless compression and cache-affinity scheduling with a claimed provable guarantee.
-
Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study
Empirical benchmarks show MoE inference cost on edge hardware tracks total parameters rather than active parameters, with OLMoE-1B-7B behind dense baselines especially on the Jetson device.
-
LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers
PreScope combines a layer-aware activation predictor, cross-layer prefetch scheduling, and asynchronous I/O to deliver 141% higher throughput and 74.6% lower latency for MoE inference on legacy hardware.
-
Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
Prism optimizes expert placement and uses runtime migration for distributed MoE inference on heterogeneous edge GPUs, achieving up to 30.6% lower latency than baselines.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.