arXiv:2607. 24665v1 Announce Type: cross Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows.
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.
DeepSeek‑V4.1‑Flash is a multimodal Mixture‑of‑Experts model with 552 B backbone parameters that supports contexts of up to one million tokens. It uses a Causal Encoder‑Decoder architecture that activates 16 B parameters per token during decoding but only 8 B during prefill, improving cost efficiency for agentic workloads. The model introduces cross‑layer KV cache reuse via Compressed Sparse Attention 2 and FP4 KV caching, reducing its global KV cache footprint to 890 bytes per token and its persistent footprint to roughly one‑eighth of the previous version, while still delivering superior performance after pretraining on a 45 T‑token multimodal corpus.
FluxMoE introduces an expert paging system that decouples Mixture-of-Experts (MoE) model experts from permanent GPU residency, allowing dynamic adaptation to available memory. By combining PagedTensor, a bandwidth‑balanced memory hierarchy, and a budget‑aware residency planner, FluxMoE streams expert weights on demand while keeping computations on GPUs. Experiments on GLM‑4.5 and Mixtral‑8×7B‑Instruct show significant throughput gains and reduced time‑per‑output‑token compared to existing inference engines, without compromising model quality.
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.
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:2606. 13392v1 Announce Type: new Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale.
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:2602. 04101v2 Announce Type: replace Abstract: We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder through a shared embedding space.
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. 14385v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have been widely adopted in real-time interactive applications such as coding assistants, real-time audio-video interaction systems.
The paper introduces a hardware-software co‑design framework that compresses Mixture‑of‑Experts (MoE) model weights into low‑precision, hardware‑native sparse representations, enabling efficient execution on Sparse Tensor Cores (SpTCs). By relaxing discrete support selection through continuous reparameterization, the method jointly optimizes quantized weights and supports a router‑weighted reconstruction objective, achieving up to 4.35 percentage‑point gains in joint sparse‑quantization accuracy while retaining 96.09% of the original model’s performance. A custom grouped sparse GEMM kernel further boosts inference speed, outperforming NVIDIA’s baseline by up to 1.65× and reducing latency by up to 4.03× on B200 GPUs.