arXiv:2608.30567v1 Announce Type: new Abstract: We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-co...
IronLLM-0.6B is a 654‑million‑parameter language model engineered for efficient on‑device inference, featuring a hybrid attention architecture, X‑MTP multi‑token prediction, and a lightweight verification head that yields a 1.48× decoding speedup. Trained on roughly 6.2 trillion tokens with a quality‑oriented pipeline and further refined via Multi‑Domain On‑Policy Distillation, the model adopts an Instruct‑Only design to meet low‑latency requirements. A lighter variant, IronLLM‑0.6B‑Light, replaces RMSNorm with Dynamic Tanh and streamlines costly components to enhance inference and quantization efficiency, offering a strong performance‑efficiency trade‑off for resource‑constrained deployment.
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.
arXiv:2606. 19348v1 Announce Type: cross Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.
arXiv:2606. 15453v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost.
arXiv:2606. 16825v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory.
UniPrefill is a prefill‑acceleration framework that works with virtually any model architecture, directly speeding up token‑level computation. It is implemented as a continuous‑batching operator and extends vLLM’s scheduling to support prefill‑decode co‑processing and tensor parallelism. The method delivers up to a 2.1× speedup in Time‑to‑First‑Token, with gains growing as concurrent requests increase.
arXiv:2608. 09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.
arXiv:2607. 22577v1 Announce Type: new Abstract: Scaling large language models (LLMs) has driven their success, yet dense Transformers couple capacity and computation: every parameter is activated for every token, making training and inference costs grow linearly with model size-a critical bottleneck as models approach trillion-parameter regimes.
arXiv:2608.30320v1 Announce Type: new Abstract: We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and a...
The paper introduces NAMOH, a native sparse attention mechanism that activates only a subset of heads per token, allowing each head to attend to a limited subsequence of tokens. By scaling the number of heads while keeping the active heads per token fixed, the method shortens head histories and reduces key‑value access without increasing overall storage. Experiments demonstrate that NAMOH can outperform fully activated models with the same parameter count and enable more efficient long‑context inference than smaller dense models.
Elastic Threshold Attention (ETA) is a trainable attention mechanism that dynamically predicts contextual thresholds from query representations, enabling selective pruning of KV cache tokens during long‑context decoding. By multiplicatively suppressing sub‑threshold logits during training, ETA avoids representation collapse and eliminates localized attention sinks, allowing a 1.45B model to match dense attention performance at roughly 85% training sparsity and 38% active decode density. At inference, a custom Triton kernel achieves up to 2.5× faster decoding on sequences up to 512K tokens, and an offline calibration step can further reduce compute by 27% by freezing per‑head thresholds.