REVIEW 16 cited by
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
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
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
read the original abstract
Large Language Models (LLMs) with the Mixture-of-Experts (MoE) architectures have shown promising performance on various tasks. However, due to the huge model sizes, running them in resource-constrained environments where the GPU memory is not abundant is challenging. Some existing systems propose to use CPU resources to solve that, but they either suffer from the significant overhead of frequently moving data between CPU and GPU, or fail to consider distinct characteristics of CPUs and GPUs. This paper proposes Fiddler, a resource-efficient inference system for MoE models with limited GPU resources. Fiddler strategically utilizes CPU and GPU resources by determining the optimal execution strategy. Our evaluation shows that, unlike state-of-the-art systems that optimize for specific scenarios such as single batch inference or long prefill, Fiddler performs better in all scenarios. Compared against different baselines, Fiddler achieves 1.26 times speed up in single batch inference, 1.30 times in long prefill processing, and 11.57 times in beam search inference. The code of Fiddler is publicly available at https://github.com/efeslab/fiddler.
Forward citations
Cited by 16 Pith papers
-
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.
-
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.
-
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.
-
MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving
ZeRO-Prefill achieves 1.35-1.59x higher throughput for MoE prefill serving by replacing per-layer activation AllToAll with overlapped asynchronous weight AllGather and prefix-aware routing.
-
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.
-
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.
-
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.
-
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.
-
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.