Specter is an inference system for mixture-of-experts (MoE) models that uses quantization to enable speculative decoding and expert offloading. By running a lightweight quantized draft model on the device, Specter predicts future expert usage and pre‑organizes expert movement, reducing PCIe I/O bottlenecks. The approach yields an average 1.50× speedup (up to 1.88×) in time per output token compared to state‑of‑the‑art systems, making single‑GPU MoE inference more practical on commodity hardware.
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv:2607. 24787v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator memory.
arXiv:2603.09983v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategie...
arXiv:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
Dynamic Expert Quantization (DynaExq) is a runtime-aware mixed-precision serving system designed for single‑GPU Mixture‑of‑Experts (MoE) inference under a hard high‑bandwidth memory (HBM) envelope. It treats the problem as an online, budget‑constrained precision allocation task, keeping the most frequently used experts at higher precision while relegating the rest to low‑precision fallbacks. By estimating expert hotness from router traces and asynchronously promoting or demoting experts, DynaExq maintains a fully materialized expert set during the forward pass, improving accuracy and throughput compared to static post‑training quantization and offloading/prefetch baselines. whyItMatters":"DynaExq enables efficient deployment of large MoE models on memory‑limited GPUs by dynamically allocating precision based on runtime expert usage, thereby reducing memory footprint and latency while boosting accuracy and throughput."
arXiv:2501.10375v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory...
SpecQuant is a training‑free framework that merges speculative decoding with multi‑parent quantization to enable adaptive, efficient inference of large language models. It generates several quantized variants (INT4, FP8, FP16) from a single base model and routes queries to the appropriate variant based on predicted complexity, using lightweight models for simple tasks and full‑precision models for complex reasoning. Evaluations on Qwen2.5 models across MMLU, AlpacaEval, and GSM8K show 35‑43% speedups with less than 2% accuracy loss, facilitating practical on‑device LLM deployment without specialized infrastructure.
arXiv:2610. 23006v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making expert offloading necessary for memory-constrained inference.
S2-MoE is a self‑speculative decoding framework designed to make Mixture‑of‑Experts (MoE) inference more efficient on edge devices. It reduces verification overhead by using routing‑aware adaptive speculative expansion, improves verification efficiency with reuse‑aware expert gating, and aligns draft and target execution through shared context. Implemented in llama.cpp, S2‑MoE delivers up to 5.3× speedup (≈2.0× on average) over standard autoregressive decoding across various MoE models and datasets on edge hardware.
The paper studies how the design of Mixture-of-Experts (MoE) routers affects inference speed when combined with Speculative Decoding (SD). It shows that routers promoting high expert coactivation reduce memory transfer costs and improve runtime. By integrating a global load‑balancing loss, shared experts, a consistency loss, and an autoregressive expert selection mechanism, the authors achieve a 21% throughput gain over baseline MoEs while preserving accuracy.
The paper introduces Cascadia, a resident inference system that runs the 975B‑parameter Inkling mixture‑of‑experts model across eleven Intel Core Ultra X7 358H AI PCs. It details a custom MoE engine that preserves routing rules, compresses graphs for OpenVINO, and coordinates FP16 expert computation with FP32 output restoration, enabling efficient deployment of six decoder layers per machine. Performance results show up to 60.29 aggregate decode tokens per second at 88 streams, with first‑token latency of 6.05 s at fifteen streams, and demonstrate that larger context budgets recover embedded code while maintaining bounded latency.