论文

RTP-LLM 是一个面向工业级 LLM 部署的高性能推理引擎，已在 Alibaba Group 成功部署，服务超过 1 亿用户，通过集成设计解决根本性瓶颈。RTP-LLM is presented, a high-performance inference engine for industrial-scale LLM deployment, successfully deployed across Alibaba Group serving over 100 million users, and addresses fundamental bottlenecks through integrated design.

本文引入一个均值修正项，有效抑制近似误差，即使在极端稀疏度下也能将性能下降保持在可控范围；并使用 PackGQA 内存访问、warp specialization 和 pingpong 流水线重新设计稀疏注意力算子。This paper introduces a mean correction term that effectively suppresses the approximation error, keeping performance degradation manageable even at extreme sparsity levels, and redesigns the sparse attention operator with PackGQA memory access, warp specialization, and pingpong pipelining.

低成本服务大语言模型日益意味着交付既经过结构压缩至部分参数、又量化到 4 bit 的模型。这两个步骤叠加后会显著降低推理、数学、代码以及长上下文能力，因此在部署前需要一个恢复（即修复）阶段。默认方案 quantization-aware training (QAT) 将压缩并量化后的模型重新拟合到硬标签；在我们的流水线中它收敛缓慢，且在峰值之后出现性能崩塌。我们转而采用 Quantization-Aware Healing (QAH)。由于结构压缩后的模型从未Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together these steps degrade reasoning, mathematics, coding, and long-context behavior enough to require a recovery, or healing, stage before deployment. The default recipe, quantization-aware training (QAT), re-fits the compressed, quantized model to hard labels; in our pipeline it converged slowly and collapsed past its peak. We adopted Quantization-Aware Healing (QAH) instead. Because a structurally compressed model is neve

GigaWorld-Policy-0.5 在保留未来视觉动力学训练收益的同时提升了机器人控制的推理效率，并引入 Mixture-of-Transformers 架构，将视觉动力学建模与动作生成分离到专门的专家模块中。GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control, and introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts.

Meshy T2在几何保真度上达到SOTA，端到端图像到网格生成中位耗时6秒，比自回归基线快一个数量级以上。Meshy T2 achieves state-of-the-art geometric fidelity and completes end-to-end image-to-mesh generation within a median of 6 seconds, over an order of magnitude faster than autoregressive baselines.

提出 MultiMedQA 基准，整合六个现有医学问答数据集（涵盖专业医学、研究与消费者查询）及一个全新的在线医学问题搜索数据集，并提出针对模型答案的人工评估框架，揭示了 LLM 在医学领域的潜在应用价值。MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, is presented and a human evaluation framework for model answers is proposed, suggesting the potential utility of LLMs in medicine.