Search

Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversity (various prefixes and tidal requests), treating all the prompts in a mixed pool is inadequate. To facilitate the similarity per scenario and minimize the inner mismatch on P/D (prefill and decoding) processing, fine-grained organization is required, dynamically adjusting P/D ratios for better performance. 2) Due to inaccurate estimation on workload (queue status or maintained connections), the global scheduler easily incurs unnecessary timeouts in prefill. 3) Block-fixed device-to-device (D2D) KVCache transfer over cluster-level RDMA (remote direct memory access) fails to achieve desired D2D utilization as expected. To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access. P/D-Serve is implemented upon Ascend and MindSpore, has been deployed over tens of thousands of NPUs for more than eight months in commercial use, and further achieves 60\%, 42\% and 46\% improvements on E2E throughput, time-to-first-token (TTFT) SLO (service level objective) and D2D transfer time. As the E2E system with optimizations, P/D-Serve achieves 6.7x increase on throughput, compared with aggregated LLMs.

We study Delaunay hypersurfaces in $\mathbb S^n$ with $n\geq 3$ and add a missing (flower) type of the category. Moreover, embedded Delaunay hypersurfaces of nonzero constant mean curvatures in $\mathbb S^n$ are found., Comment: Improved version with more contents and updated figures, 17 pages

Current point cloud registration methods are mainly based on local geometric information and usually ignore the semantic information contained in the scenes. In this paper, we treat the point cloud registration problem as a semantic instance matching and registration task, and propose a deep semantic graph matching method (DeepSGM) for large-scale outdoor point cloud registration. Firstly, the semantic categorical labels of 3D points are obtained using a semantic segmentation network. The adjacent points with the same category labels are then clustered together using the Euclidean clustering algorithm to obtain the semantic instances, which are represented by three kinds of attributes including spatial location information, semantic categorical information, and global geometric shape information. Secondly, the semantic adjacency graph is constructed based on the spatial adjacency relations of semantic instances. To fully explore the topological structures between semantic instances in the same scene and across different scenes, the spatial distribution features and the semantic categorical features are learned with graph convolutional networks, and the global geometric shape features are learned with a PointNet-like network. These three kinds of features are further enhanced with the self-attention and cross-attention mechanisms. Thirdly, the semantic instance matching is formulated as an optimal transport problem, and solved through an optimal matching layer. Finally, the geometric transformation matrix between two point clouds is first estimated by the SVD algorithm and then refined by the ICP algorithm. Experimental results conducted on the KITTI Odometry dataset demonstrate that the proposed method improves the registration performance and outperforms various state-of-the-art methods., Comment: 12 pages, 6 figures

This paper exhibits a structural strategy to produce new minimal submanifolds in spheres based on two given ones. The method is to spin the given minimal submanifolds by a curve $\gamma\subset \mathbb S^3$ in a balanced way and leads to resulting minimal submanifolds $-$ spiral minimal products, which form a two-dimensional family arising from intriguing pendulum phenomena decided by $C$ and $\tilde C$. With $C=0$, we generalize the construction of minimal tori in $\mathbb S^3$ explained in [Bre13] to higher dimensional situations. When $C=-1$, we recapture previous relative work in [CLU06] and [HK12] for special Legendrian submanifolds in spheres, and moreover, can gain numerous $\mathscr C$-totally real and totally real embedded minimal submanifolds in spheres and in complex projective spaces respectively. A key ingredient of the paper is to apply a beautiful extension result of minimal submanifolds by Harvey and Lawson [HL75] for a rotational reflection principle in our situation to establish curve $\gamma$., Comment: Further improved version (52 pages, 10 figures), to be submitted

The recent report of near-ambient superconductivity in nitrogen doped lutetium hydride has triggered a worldwide fanaticism and raised major questions about the latest claims. An intriguing phenomenon of color changes in pressurized samples from blue to pink to red was observed and correlated with the claimed superconducting transition, but the origin and underlying physics of these color changes have yet to be elucidated. Here we report synthesis and characterization of high-purity nitrogen doped lutetium hydride LuH$_{2\pm\text{x}}$N$_y$ with the same structure and composition as in the main phase of near-ambient superconductor1. We find a new purple phase of LuH$_{2\pm\text{x}}$N$_y$ between blue and pink phase, and reveal that the sample color changes likely stem from pressure-driven redistribution of nitrogen and its interaction with the LuH$_2$ framework. No superconducting transition is found in all blue, purple, pink and red phases at temperatures 1.8-300 K and pressures 0-30 GPa. Instead, we identify a notable temperature-induced resistance anomaly of structural and/or electronic origin in LuH$_{2\pm\text{x}}$N$_y$, which is most pronounced in the pink phase and may have been erroneously interpreted as a sign of superconducting transition. This work establishes key benchmarks for nitrogen doped lutetium hydrides, allowing an in-depth understanding of the novel pressure-induced phase changes., Comment: 17 pages and 5 figures in the main text. 9 pages and 12 figures in the Supplementary Material. Any valuable comments and suggestions are warmly welcomed

We investigate the nonequilibrium photocarrier dynamics of WTe2 under pressure using the optical pump-probe spectroscopy. The pressure dependences of the electronic relaxation manifest anomalous changes around 0.8, 3.5, and 6 GPa, indicating the abruptions in the electron-phonon interactions. In addition, the coherent phonon oscillations originating from shear mode suddenly disappears above 3.5 GPa, which marks the onset of Td-1T' structural phase transition. Supported by the theoretical calculation, we unveil the electronic topological transitions (ETTs), especially an emergence of a new type-II Weyl point for Td-WTe2 under pressure. Our work demonstrates a novel route to probe the ETTs under pressure., Comment: 8 pages, 3 figures

Let $G$ be a compact connected subgroup of $SO(n+1)$. In $\mathbb{R}^{n+1}$, we gain interior $G$-symmetry for minimal hypersurfaces and hypersurfaces of constant mean curvature (CMC) which have $G$-invariant boundaries and $G$-invariant contact angles along boundaries. The main ingredients of the proof are to build an associated Cauchy problem based on infinitesimal Lie group actions, and to apply Morrey's regularity theory and the Cauchy-Kovalevskaya Theorem. Moreover, we also investigate the same kind of symmetry inheritance from boundaries for hypersurfaces of constant higher order mean curvature and Helfrich-type hypersurfaces in $\mathbb{R}^{n+1}$., Comment: 25 pages, 8 figures; Revised, results unchanged

We study the Faraday patterns generated by spin-orbit-coupling induced parametric resonance in a spinor Bose-Einstein condensate with repulsive interaction. The collective elementary excitations of the Bose-Einstein condensate, including density waves and spin waves, are coupled as the result of the Raman-induced spin-orbit coupling and a quench of the relative phase of two Raman lasers without the modulation of any of the system's parameters. We observed several higher parametric resonance tongues at integer multiples of the driving frequency and investigated the interplay between Faraday instabilities and modulation instabilities when we quench the spin-orbit-coupled Bose-Einstein condensate from zero-momentum phase to plane-wave phase. If the detuning is equal to zero, the wave number of combination resonance barely changes as the strength of spin-orbit coupling increases. If the detuning is not equal to zero after a quench, a single combination resonance tongue will split into two parts.

How two-party entanglement (TPE) is distributed in the many-body systems? This is a fundamental issue because the total TPE between one party with all the other parties, $\mathcal{C}^N$, is upper bounded by the Coffman, Kundu and Wootters (CKW) monogamy inequality, from which $\mathcal{C}^N \le \sqrt{N-1}$ can be proved by the geometric inequality. Here we explore the total entanglement $\mathcal{C}^\infty$ and the associated total tangle $\tau^\infty$ in a $p$-wave free fermion model with long-range interaction, showing that $\mathcal{C}^\infty \sim \mathcal{O}(1)$ and $\tau^\infty$ may become vanishing small with the increasing of long-range interaction. However, we always find $\mathcal{C}^\infty \sim 2\xi \tau^\infty$, where $\xi$ is the truncation length of entanglement, beyond which the TPE is quickly vanished, hence $\tau^\infty \sim 1/\xi$. This relation is a direct consequence of the exponential decay of the TPE induced by the long-range interaction. These results unify the results in the Lipkin-Meshkov-Glick (LMG) model and Dicke model and generalize the Koashi, Buzek and Imono bound to the quantum many-body models, with much broader applicability.