Author

Xiaohongshu Tech REDtech

Official account of the Xiaohongshu tech team, sharing tech innovations and problem insights, advancing together.

134

Articles

Likes

913

Views

Comments

Latest from Xiaohongshu Tech REDtech

100 recent articles max

Xiaohongshu Tech REDtech

Mar 4, 2026 · Mobile Development

How Xiaohongshu Delivered Billion‑User Voice & Fireworks Effects with Adaptive Rendering

During the 2026 Chinese New Year, Xiaohongshu built a real‑time dynamic interaction system that combined adaptive scheduling, high‑performance particle rendering, and industrial‑grade ASR to deliver synchronized voice greetings and emoji fireworks to over a billion daily active users across heterogeneous mobile devices.

ASRCross-platformReal-time Rendering

0 likes · 13 min read

How Xiaohongshu Delivered Billion‑User Voice & Fireworks Effects with Adaptive Rendering

Xiaohongshu Tech REDtech

Feb 5, 2026 · Databases

How RedSQL Supercharged MySQL Performance and Achieved Zero‑Data‑Loss Replication

This article details Xiaohongshu's RedSQL MySQL kernel project, describing three major solutions—high‑throughput seckill optimization, a Binlog Server‑based zero‑data‑loss replication scheme, and second‑level DDL column addition—along with additional kernel enhancements that together delivered multi‑fold performance gains and improved stability.

DDLData ConsistencyMySQL

0 likes · 12 min read

How RedSQL Supercharged MySQL Performance and Achieved Zero‑Data‑Loss Replication

Xiaohongshu Tech REDtech

Jan 30, 2026 · Backend Development

How Java Virtual Threads Cut Latency by 31× and Slash CPU Use in Production

This article explains the principles of Java virtual threads, compares them with traditional platform threads, details RedJDK21’s implementation and performance improvements—including up to 31‑fold latency reduction and 24% CPU savings—in large‑scale services at XiaoHongShu, and discusses migration challenges, lock handling, monitoring, and future roadmap.

JVMJavaRedJDK21

0 likes · 29 min read

How Java Virtual Threads Cut Latency by 31× and Slash CPU Use in Production

Xiaohongshu Tech REDtech

Jan 19, 2026 · Databases

How Merged Seckill Boosts MySQL Write Throughput 5× for High‑Traffic E‑Commerce

The article details a MySQL kernel‑level merged‑seckill optimization that replaces traditional queue‑based flash‑sale handling, achieving up to 5.5× higher TPS (up to 23,543 TPS on 128 threads) and sustaining 1.5W+ orders per second, while remaining transparent to applications and preserving compatibility with existing SQL.

CacheLockMySQL

0 likes · 11 min read

How Merged Seckill Boosts MySQL Write Throughput 5× for High‑Traffic E‑Commerce

Xiaohongshu Tech REDtech

Jan 15, 2026 · Information Security

How Hi-Guard Improves Trustworthy Multimodal Content Moderation with Policy‑Aligned Reasoning

The Hi-Guard framework transforms content moderation by aligning multimodal models with policy rules through hierarchical prompting, a structured taxonomy, and soft‑margin reinforcement learning, achieving significant gains in accuracy, precision, recall, and explainability for large‑scale user‑generated content platforms.

content moderationexplainabilityhierarchical labeling

0 likes · 9 min read

How Hi-Guard Improves Trustworthy Multimodal Content Moderation with Policy‑Aligned Reasoning

Xiaohongshu Tech REDtech

Dec 11, 2025 · Artificial Intelligence

Fine‑Grained Activation Offloading: Cutting Memory Use While Preserving LLM Throughput

The article introduces a fine‑grained activation offloading technique implemented in Megatron‑Core that offloads module‑level activations to CPU, overlaps transfer with computation, and remains compatible with pipeline and virtual pipeline parallelism, dramatically reducing peak GPU memory for large language models while incurring minimal throughput loss.

LLMMegatronactivation offloading

0 likes · 18 min read

Fine‑Grained Activation Offloading: Cutting Memory Use While Preserving LLM Throughput

Xiaohongshu Tech REDtech

Dec 4, 2025 · Artificial Intelligence

CrossVid: A New Benchmark Reveals the Limits of Multimodal LLMs in Cross‑Video Reasoning

CrossVid is an open‑source benchmark that evaluates multimodal large language models on cross‑video reasoning tasks, providing 5,331 videos, 9,015 QA pairs, four high‑level dimensions and ten specific tasks, and exposing significant performance gaps between current models and humans.

AI evaluationMultimodal LLMVideo Understanding

0 likes · 9 min read

CrossVid: A New Benchmark Reveals the Limits of Multimodal LLMs in Cross‑Video Reasoning

Xiaohongshu Tech REDtech

Nov 20, 2025 · Artificial Intelligence

How DeepAgent Achieves End‑to‑End Reasoning with 16,000+ Scalable Tools

DeepAgent is a new end‑to‑end reasoning agent that unifies autonomous thinking, dynamic tool search, and execution, handling over 16,000 real APIs, supporting embodied environments and research assistance, and achieving state‑of‑the‑art results across multiple benchmarks through its unified reasoning core, memory‑folding mechanisms, structured memory, and the ToolPO training framework.

AI AgentsGeneral AITool Integration

0 likes · 14 min read

How DeepAgent Achieves End‑to‑End Reasoning with 16,000+ Scalable Tools

Xiaohongshu Tech REDtech

Nov 10, 2025 · R&D Management

How AI Is Redefining Engineering Teams: From Code Monkeys to Value Creators

In the AI‑native era, engineers spend most of their time on meetings and coordination rather than coding, prompting a shift toward networked, task‑oriented teams where AI acts as a collaborative agent, enabling smaller, high‑output groups that focus on value creation instead of mere implementation.

AIEngineering Managementsoftware development

0 likes · 9 min read

How AI Is Redefining Engineering Teams: From Code Monkeys to Value Creators

Xiaohongshu Tech REDtech

Nov 4, 2025 · Artificial Intelligence

Unveiling the Law of Capacity Gap: Boosting Language Model Distillation Efficiency

At ACL 2025, a collaborative paper introduced the Law of Capacity Gap, revealing a linear 2.5× optimal teacher‑student size relationship in language model distillation, dramatically cutting compute costs and achieving Pareto‑optimal efficiency, with the MiniMA model as a successful demonstration.

MiniMAartificial-intelligencecapacity-gap

0 likes · 7 min read

Unveiling the Law of Capacity Gap: Boosting Language Model Distillation Efficiency