arXiv:2608. 09444v1 Announce Type: new Abstract: A main promise of looped language models (LMs) is depth-adaptive inference.
arXiv:2609.15160v1 Announce Type: new Abstract: Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across mul...
arXiv:2412. 04504v2 Announce Type: replace-cross Abstract: As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical.
arXiv:2606. 00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) inference due to its efficiency in maximizing compute and memory utilization.
arXiv:2504. 11320v4 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day.
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.
T-LoopFormer introduces token-level elastic-depth looped transformers that allow each token to decide its own number of loop iterations based on its hidden state, improving token generation accuracy. It also adds a recursion-wise key‑value cache so tokens at different depths only attend to their corresponding cached states, speeding up autoregressive decoding. Experiments demonstrate strong performance on language modeling and zero‑shot reasoning, achieving the lowest decoding latency among comparable models.
arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.
GroupKV is a lightweight hierarchical KV cache management system designed for long‑context diffusion large language model (dLLM) inference. It partitions the context into contiguous groups and uses coarse‑to‑fine sparse selection, cross‑layer consistency for predictive prefetching, and a staleness correction mechanism to keep the cache coherent amid dynamic KV updates. The approach also incorporates streaming prefill to lower peak memory usage, achieving up to 48× longer serviceable context, 3.73× faster inference in offload‑based settings, and competitive task accuracy.
arXiv:2608.28044v1 Announce Type: cross Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes t...
arXiv:2607. 04206v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation.
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.
The paper introduces CHASE, a cache‑hole‑adapted skip‑exit mechanism for looped state‑space language models, specifically Looped Mamba and Looped Hybrid Mamba‑Transformer. It shows that looping these architectures improves performance on controlled reasoning tasks and remains competitive in pre‑training benchmarks while using fewer distinct parameters. The cache‑hole adaptation allows selective skipping of recurrent steps during inference, maintaining perplexity close to full computation and achieving significant speedups.