Author

Tencent Technical Engineering

Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.

124

Articles

Likes

1.0k

Views

Comments

Latest from Tencent Technical Engineering

100 recent articles max

Tencent Technical Engineering

Aug 5, 2026 · Artificial Intelligence

Advanced AI Infra: Making Large Language Models Produce Deterministic Outputs

This article analyzes why LLM inference often yields nondeterministic results, explains how floating‑point addition order, GEMM tiling, Split‑K, RMSNorm, FlashAttention, and NCCL all contribute to batch variance, and details the engineering steps vLLM takes to enforce batch‑invariant execution across GPUs.

Batch InvarianceDeterminismFlashAttention

0 likes · 52 min read

Advanced AI Infra: Making Large Language Models Produce Deterministic Outputs

Tencent Technical Engineering

Jun 30, 2026 · Mobile Development

Building a Multi‑Modal Chat App for Android, iOS, and HarmonyOS in 7.5 Hours with AI‑Powered Kuikly

In a single day the author used Kuikly’s Kotlin‑Multiplatform framework together with AI‑driven CodeBuddy to generate roughly 3,500 lines of code, integrate six ready‑made components, write two custom modules, debug an image‑loading issue, and ship a fully functional multi‑modal chat app that runs on Android, iOS and HarmonyOS without writing a single line of code manually.

AI codingCustom ModuleKotlin Multiplatform

0 likes · 15 min read

Building a Multi‑Modal Chat App for Android, iOS, and HarmonyOS in 7.5 Hours with AI‑Powered Kuikly

Tencent Technical Engineering

May 28, 2026 · R&D Management

When AI Becomes a Mirror: The Silent Revolution of Writing Specs

The article argues that in the AI era, writing specifications, rules, and evaluation sets forces engineers to externalize tacit knowledge, turning AI from a tool into a mirror that reveals hidden assumptions, and warns that this legibility brings both powerful benefits and profound risks.

AIGoodhart's LawSpec-Driven Development

0 likes · 28 min read

When AI Becomes a Mirror: The Silent Revolution of Writing Specs

Tencent Technical Engineering

May 27, 2026 · Artificial Intelligence

Marvis Hands‑On Review: Six AI Agents Take Over My Desktop

The author evaluates Marvis, an AI‑powered desktop assistant that bundles six specialized agents—fast terminal scheduling, autonomous planning, cross‑modal task chains, a visual agent workspace, vibecoding for code, and desktop organization—showcasing rapid local execution, privacy‑preserving design, multi‑agent coordination, and future mobile integration.

AI assistantDesktop AutomationLocal AI

0 likes · 15 min read

Marvis Hands‑On Review: Six AI Agents Take Over My Desktop

Tencent Technical Engineering

May 26, 2026 · Information Security

AI Era Vulnerability Benchmark Revamp: 3,632 CVE Insights & VulnGym Release

Analyzing 3,632 high‑severity GitHub Advisory reports from 2025‑2026, the authors reveal a sharp rise in business‑logic flaws—especially in high‑star projects—prompting a redesign of vulnerability‑detection benchmarks, and introduce VulnGym, a real‑project, white‑box dataset with 400+ paths and detailed entry‑point, trace, and critical‑operation annotations.

AI securityBusiness Logic Bugsbenchmark

0 likes · 17 min read

AI Era Vulnerability Benchmark Revamp: 3,632 CVE Insights & VulnGym Release

Tencent Technical Engineering

May 25, 2026 · Artificial Intelligence

vLLM Deep Dive: Continuous Batching and Paged Attention for Fast LLM Inference

This article walks through a two‑month source‑code study of vLLM, explaining how token‑level scheduling, continuous batching, and the Paged Attention mechanism reshape tensor dimensions to turn large‑model inference into a compute‑bound, high‑throughput process while managing GPU memory efficiently.

FlashAttentionGPU OptimizationLLM inference

0 likes · 29 min read

vLLM Deep Dive: Continuous Batching and Paged Attention for Fast LLM Inference

Tencent Technical Engineering

May 24, 2026 · Artificial Intelligence

How Tsinghua & Tencent Mixed‑X Won the MLSys 2026 MoE Inference Challenge with a 4.1× Speedup

The Tsinghua‑Tencent Mixed‑X team captured the MLSys 2026 MoE inference optimization championship by analyzing NPU bottlenecks, redesigning data movement, applying expert‑level sharding, continuous DMA, PSUM batching, and an Agent‑based optimizer, achieving a 4.1× end‑to‑end speedup while preserving bit‑level output fidelity.

Agent optimizerInference OptimizationMLSys 2026

0 likes · 14 min read

How Tsinghua & Tencent Mixed‑X Won the MLSys 2026 MoE Inference Challenge with a 4.1× Speedup

Tencent Technical Engineering

Apr 23, 2026 · Artificial Intelligence

Tencent Hunyuan Launches Hy3 Preview: Open‑Source Model Boosts Agent Performance

On April 23, Tencent released the open‑source Hy3 preview, a 295 B‑parameter hybrid expert model with 21 B active parameters and 256K context length, delivering substantial gains in complex reasoning, instruction following, code and agent tasks, achieving 40 % faster inference, lower costs, and strong benchmark results across Tencent’s AI products.

Hy3-previewLarge Language ModelTencent Hunyuan

0 likes · 9 min read

Tencent Hunyuan Launches Hy3 Preview: Open‑Source Model Boosts Agent Performance

Tencent Technical Engineering

Apr 21, 2026 · Backend Development

Can AI Safely Write Code for High‑Risk Backend Systems? Lessons from Tencent’s CDN LEGO Project

When AI coding hype focuses on front‑end page generation, the real challenge is whether AI can be trusted to write code for a million‑line, high‑availability CDN backend; this article details Tencent’s systematic exploration, a 20‑day Rust proxy prototype, a five‑layer Harness Engineering framework, and concrete data showing both breakthroughs and remaining risks.

AI codingHarness Engineeringbackend development

0 likes · 25 min read

Can AI Safely Write Code for High‑Risk Backend Systems? Lessons from Tencent’s CDN LEGO Project

Tencent Technical Engineering

Apr 20, 2026 · R&D Management

How AI Can Automate the Entire Software Delivery Pipeline from Requirement to Deployment

The article outlines a multi‑stage AI‑driven automation roadmap that extends from requirement gathering through technical solution generation, code creation, testing, and deployment, detailing challenges such as workflow standardization, knowledge‑base construction, skill reuse, and quality assurance, and presents concrete metrics showing up to 80% efficiency gains.

AI automationAI codingDevOps

0 likes · 16 min read

How AI Can Automate the Entire Software Delivery Pipeline from Requirement to Deployment