arXiv:2607. 28097v1 Announce Type: new Abstract: Mathematically equivalent expert-reduction orders can produce observably different sparse-MoE executions.
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.
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:2606. 07404v1 Announce Type: new Abstract: This paper reports on training a hundred-billion-parameter sparse mixture of experts on a single eight-GPU node, end to end.
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:2609.24698v1 Announce Type: new Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which foll...
The paper introduces Routide, a Swift/MLX runtime that runs a quantized Qwen3.6-35B-A3B model on iPhone by keeping expert weights on device storage and a byte‑budgeted subset in memory. It evaluates cache‑policy effects, showing that a 512 MiB LRU cache yields 0.00% demand hits while a 576 MiB LRU reaches 38.58% hits across five 128‑token workloads, indicating that capacity limits depend on policy and workload. The study also reports memory footprints, thermal events, and power estimates, demonstrating that flash‑backed MoE inference is feasible within bounded resources but has measurable limitations.
arXiv:2608. 15383v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models reduce arithmetic by activating only a small subset of experts per token, yet deployment still requires storing and moving the full expert bank.
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.
arXiv:2608. 03447v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel.
arXiv:2607. 28166v2 Announce Type: replace-cross Abstract: Diffusion language models expose a provisional prediction at every denoising step, and on many tasks the candidate answer inside it stabilizes before the step schedule is exhausted.
The paper introduces Inference‑Native Zeroth‑Order (ZO) optimization, which redefines ZO as a query‑based process that can be executed directly by inference runtimes. By exposing ZO’s query semantics and using abstractions such as ProbePlan, factorized side states, and persistent subspace reuse, the method reduces state‑management cost and DRAM traffic dramatically. Experiments on large models (OPT‑13B, Qwen3‑8B) show that inference‑native steps are nearly identical to matched‑query controls while achieving significant memory savings and efficient batching.
arXiv:2607. 14427v1 Announce Type: new Abstract: A depth-recurrent transformer applies a weight-tied core a variable number of times, and prior work has shown that training with a randomized recursion count yields one checkpoint usable across a range of inference depths.