Author

AntTech

Technology is the core driver of Ant's future creation.

715

Articles

Likes

3.3k

Views

Comments

Latest from AntTech

100 recent articles max

AntTech

Nov 27, 2025 · Artificial Intelligence

How AMem NCCL‑Plugin Cuts GPU Memory Overhead for Trillion‑Parameter RL Models

The article explains the design, implementation, and performance of the AMem NCCL‑Plugin, a lightweight extension to NVIDIA's NCCL that enables transparent offloading and rapid recovery of GPU memory during reinforcement‑learning training of trillion‑parameter models, detailing its architecture, APIs, benchmarks, installation steps, and integration guidelines.

ASystemDistributed TrainingGPU

0 likes · 18 min read

How AMem NCCL‑Plugin Cuts GPU Memory Overhead for Trillion‑Parameter RL Models

AntTech

Nov 21, 2025 · Artificial Intelligence

How Awex Enables Sub‑Second TB‑Scale Weight Sync for Trillion‑Parameter RL Models

Awex is a high‑performance Python framework that synchronizes training and inference weights for trillion‑parameter reinforcement‑learning models in seconds, using unified conversion, metadata management, and NCCL/RDMA transfer plans, dramatically reducing RL training latency and supporting diverse parallel strategies.

Distributed TrainingPythonhigh-performance computing

0 likes · 17 min read

How Awex Enables Sub‑Second TB‑Scale Weight Sync for Trillion‑Parameter RL Models

AntTech

Nov 11, 2025 · Artificial Intelligence

Breaking the Efficiency Wall: Ant Group’s Bailing Model Paves the Way to AGI

At CNCC 2025, Ant Group’s Vice President Zhou Jun outlined the Bailing large‑model’s five‑layer architecture, hybrid linear attention, Ling Scaling Law, and novel training algorithms that dramatically cut costs and latency, achieving state‑of‑the‑art performance on math and code benchmarks while promoting open‑source collaboration toward AGI.

AGIMixture of ExpertsScaling Laws

0 likes · 8 min read

Breaking the Efficiency Wall: Ant Group’s Bailing Model Paves the Way to AGI

AntTech

Nov 8, 2025 · Artificial Intelligence

Ant Group’s AntBaiLing Model: Pushing AI Scaling Limits with Trillion‑Parameter Efficiency

Ant Group’s President Luo Ji outlined how the AntBaiLing suite, featuring trillion‑parameter open‑source models, three efficiency breakthroughs, and a domestic compute cluster, is advancing AGI research and inclusive applications, especially in healthcare, while emphasizing ethical, trustworthy AI.

AGIlarge language modelsmodel efficiency

0 likes · 5 min read

Ant Group’s AntBaiLing Model: Pushing AI Scaling Limits with Trillion‑Parameter Efficiency

AntTech

Nov 4, 2025 · Artificial Intelligence

Unlock Native TPU Inference with SGLang-Jax: A Jax‑Powered Open‑Source Engine

SGLang-Jax is a cutting‑edge, fully Jax‑based open‑source inference engine that delivers native TPU performance, integrates advanced features like continuous batching, tensor and expert parallelism, and speculative decoding, while providing detailed installation and usage guidance for developers.

JAXSGLang-JaxTPU inference

0 likes · 10 min read

Unlock Native TPU Inference with SGLang-Jax: A Jax‑Powered Open‑Source Engine

AntTech

Nov 3, 2025 · Information Security

What Does the New IEEE 3169‑2025 Standard Mean for Privacy‑Preserving Computation Security?

The IEEE 3169‑2025 standard, led by Ant Group, introduces a unified five‑level security grading framework for privacy‑preserving computation across technologies like MPC, federated learning and TEEs, detailing attack‑defense effectiveness, information leakage categories, and additional metrics to guide secure data‑flow implementations.

Data SecurityIEEE 3169information security

0 likes · 6 min read

What Does the New IEEE 3169‑2025 Standard Mean for Privacy‑Preserving Computation Security?

AntTech

Oct 29, 2025 · Artificial Intelligence

Inside Ant’s Baoling: Balancing Efficiency and Reasoning in a 1‑Trillion‑Parameter Model

At the Ant Star Innovation Journey event, the Baoling team unveiled their roadmap for trillion‑parameter models, detailing the development of Ling‑1T, Ring‑1T and multimodal Ming series, the scaling‑law‑guided architecture, training innovations, evaluation methods, and open‑source releases that aim to advance efficient, high‑performance AI.

Efficient Inferencelarge language modelscaling law

0 likes · 24 min read

Inside Ant’s Baoling: Balancing Efficiency and Reasoning in a 1‑Trillion‑Parameter Model

AntTech

Oct 28, 2025 · Artificial Intelligence

Ming-Flash-Omni-Preview: 103B Open-Source Multimodal Model Excelling in Image, Video, and Speech

Introducing Ming‑Flash‑Omni‑Preview, a 103‑billion‑parameter open‑source multimodal model built on a sparse MoE architecture that delivers state‑of‑the‑art performance in controllable image generation, streaming video understanding, and context‑aware speech recognition, surpassing prior models on GenEval and GEdit benchmarks.

Sparse MoEVideo Understandingimage generation

0 likes · 8 min read

Ming-Flash-Omni-Preview: 103B Open-Source Multimodal Model Excelling in Image, Video, and Speech

AntTech

Oct 26, 2025 · Databases

How LCL+ Boosts Distributed Database Performance with One‑Victim Deadlock Resolution

The OceanBase team’s LCL+ algorithm, a lock‑chain‑length based distributed deadlock detection and elimination method, eliminates the need for a global wait‑for graph, achieves single‑victim unlocks, and dramatically improves throughput while reducing tail latency in production database clusters.

Deadlock DetectionOceanBasedatabase algorithms

0 likes · 7 min read

How LCL+ Boosts Distributed Database Performance with One‑Victim Deadlock Resolution

AntTech

Oct 21, 2025 · Mobile Development

Why Does Hybrid Composition Crash with ‘No Surface’ Errors on Android Mini‑Programs?

This article analyzes a recurring crash in Android mini‑programs caused by a canvas synchronization issue in hybrid composition, detailing the stack traces, EGL surface creation failures, cross‑process SurfaceTexture lifecycle problems, and the concrete fix that dramatically reduced “no surface” crashes.

Android RenderingCrash analysisEGL

0 likes · 20 min read

Why Does Hybrid Composition Crash with ‘No Surface’ Errors on Android Mini‑Programs?