arXiv:2608. 08627v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes over its full expert bank.
arXiv:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...
arXiv:2608. 02989v1 Announce Type: new Abstract: Speculative decoding verifies a tree of draft tokens in one target-model forward pass.
arXiv:2608. 08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs.
IntBMoE introduces a block‑conditioned mixture‑of‑experts that decouples participation, execution, and materialization by combining dense expert composition with sparse block execution. Each internal layer uses a lightweight hypernetwork to merge all expert bases into a single composed expert, while a router selects only a few blocks per token, keeping compute and memory costs low. Experiments on image classification, language modeling, and sequential recommendation demonstrate consistent performance gains, and the model is deployed in AMap’s generative recommendation system, improving UVCTR by 2.4% in online A/B tests.
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
arXiv:2607. 08782v1 Announce Type: cross Abstract: Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models.
arXiv:2606. 09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall: the full expert pool must remain resident to support token-dependent routing.
arXiv:2510. 02345v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.
ExFold is a training‑free expert‑folding framework that jointly accelerates the prefill and decode phases of Mixture‑of‑Experts (MoE) models by projecting the contributions of excluded experts onto a retained expert set using calibrated scalar projectors. It treats both phases as a budgeted output‑approximation problem, achieving token‑level Top‑K folding for prefill and batch‑level expert‑pool folding for decode. Implemented as a plug‑and‑play plugin in vLLM with a lightweight CUDA kernel, ExFold delivers up to 1.41× TTFT and 2.45× TPOT speedups while preserving about 99% of the original model quality.
The paper proposes a method for routing requests to a fixed pool of quantized Mixture-of-Experts (MoE) instances, aiming to maximize throughput while respecting a quality‑degradation budget. It introduces Fragility‑Weighted Perplexity (FWP) as a request‑specific risk metric derived from prompt tokens, and uses a window‑level linear program to compute a reduced‑reward score that aligns with the LP optimum. Experiments on Qwen prompts show that FWP‑based allocation improves throughput by 2.5% over request‑agnostic mixing and static configurations.
arXiv:2602. 19938v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets.
arXiv:2510. 19366v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs).