arXiv:2602. 06932v5 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem.
arXiv:2606. 18967v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities.
arXiv:2512. 22420v5 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel.
TIDE (Temporal Incremental Draft Engine) is a serving‑engine‑native framework that integrates online draft adaptation into high‑performance LLM inference. By reusing intermediate hidden states from the target model as training signals, TIDE avoids extra target model computation and serving‑time overhead, activating speculation and draft training only when beneficial. On heterogeneous GPU clusters, TIDE achieves up to 1.66× higher throughput than no‑speculation baselines, reduces training time by up to 3.02×, cuts storage needs by 24×, and improves system throughput by up to 1.22×.
arXiv:2607. 03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations.
arXiv:2608. 04962v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but autoregressive rollout generation remains a major efficiency bottleneck.
arXiv:2605. 21312v2 Announce Type: replace-cross Abstract: Modern LLM serving is no longer homogeneous or monolithic.
arXiv:2608. 19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain.
arXiv:2607. 05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification.
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.
FlexEE is an early‑exiting framework designed for large language model inference that is constrained by computation and memory, particularly in offloading‑based deployments. It uses layer‑wise exit supervision, self‑speculative decoding over a Top‑K local vocabulary, and dynamic hidden‑state management to enable reliable intermediate‑layer predictions and memory‑aware execution. Experiments on Llama2‑7B and Llama3‑8B show that FlexEE achieves significant speedups—up to 1.27×/3.16× and 1.25×/2.83× respectively—while maintaining minimal accuracy loss.
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.
AsyncFlow is an asynchronous streaming reinforcement learning framework designed to improve the post‑training phase of large language models. It introduces a distributed data storage and transfer module that enables panoramic data management and fine‑grained scheduling, allowing automated pipeline overlapping and dynamic load balancing. The framework also employs an asynchronous producer‑consumer workflow to reduce computational idleness by deferring parameter updates within staleness thresholds, and it is architecturally decoupled from training and inference engines, providing modular, customizable user interfaces. Experiments show an average throughput improvement of 1.59× over the state‑of‑the‑art baseline.