MoE-Prefill achieves 1.35-1.59x higher throughput for prefill-only MoE serving by using asynchronous expert parallelism to overlap weight AllGather with computation and prefix-aware routing with true-FLOPs tracking.
Fid- dler: Cpu-gpu orchestration for fast inference of mixture- of-experts models.arXiv preprint arXiv:2402.07033
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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.
A CPU-GPU hybrid design with stream-loading prefill, expert parallelism, and disaggregation achieves cloud SLOs for local MoE inference on dual-socket CPUs and consumer GPUs.
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.
DAK enables direct GPU access to remote memory for LLM inference via TMA repurposing and a greedy offloading algorithm, achieving up to 3x gains over prefetching baselines on NVLink-C2C and 1.8x on PCIe.
Lynx exploits training-induced batch-level expert activation skews via AffinityBinning to reduce invoked experts per batch, delivering up to 1.30x throughput with under 1% accuracy loss across four model families.
CAEE reduces MoE inference latency 8-18% on 671B DeepSeek-R1 by cost-aware expert pruning and low-overhead compensation while keeping accuracy drop under 1%.
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 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.
HCInfer recovers up to 5.2% accuracy over compressed LLMs and delivers 10.4x speedup versus full-precision models by offloading compensation parameters to CPU with async execution on resource-limited hardware.
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.
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.
citing papers explorer
-
MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving
MoE-Prefill achieves 1.35-1.59x higher throughput for prefill-only MoE serving by using asynchronous expert parallelism to overlap weight AllGather with computation and prefix-aware routing with true-FLOPs tracking.
-
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.
-
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
A CPU-GPU hybrid design with stream-loading prefill, expert parallelism, and disaggregation achieves cloud SLOs for local MoE inference on dual-socket CPUs and consumer GPUs.
-
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.
-
DAK: Direct-Access-Enabled GPU Memory Offloading with Optimal Efficiency for LLM Inference
DAK enables direct GPU access to remote memory for LLM inference via TMA repurposing and a greedy offloading algorithm, achieving up to 3x gains over prefetching baselines on NVLink-C2C and 1.8x on PCIe.
-
Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection
Lynx exploits training-induced batch-level expert activation skews via AffinityBinning to reduce invoked experts per batch, delivering up to 1.30x throughput with under 1% accuracy loss across four model families.
-
Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference
CAEE reduces MoE inference latency 8-18% on 671B DeepSeek-R1 by cost-aware expert pruning and low-overhead compensation while keeping accuracy drop under 1%.
-
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.
-
HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices
HCInfer recovers up to 5.2% accuracy over compressed LLMs and delivers 10.4x speedup versus full-precision models by offloading compensation parameters to CPU with async execution on resource-limited hardware.
-
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.
-
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.