Author

Xiaohongshu Tech REDtech

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

126

Articles

Likes

650

Views

Comments

Latest from Xiaohongshu Tech REDtech

100 recent articles max

Xiaohongshu Tech REDtech

Jul 16, 2026 · Artificial Intelligence

Cut First‑Token Latency by 3.25×: Introducing HYPIC for Position‑Independent Caching in Hybrid‑Attention LLMs

HYPIC combines position‑independent caching with hybrid‑attention LLMs, reducing first‑token latency by 3.25× and sustaining QPS by 1.66× while keeping quality loss under 2 points, through a segment‑cumulative transition operator, a seam‑window fix for full‑attention layers, and segment‑parallel execution.

HYPICHybrid AttentionKV cache

0 likes · 13 min read

Cut First‑Token Latency by 3.25×: Introducing HYPIC for Position‑Independent Caching in Hybrid‑Attention LLMs

Xiaohongshu Tech REDtech

Jul 14, 2026 · Artificial Intelligence

How Xiaohongshu Built an Enterprise AI Personal Assistant from Zero to Full‑Staff Coverage

Xiaohongshu’s AI team describes a month‑long, three‑person effort that leveraged an AI‑Native project model, isolated Kubernetes clusters, a custom sandbox (NEX), token‑saving Self‑GC, cost‑aware routing, and a three‑layer memory architecture to roll out a secure, low‑cost AI personal assistant used by every employee.

AI AgentCost OptimizationMemory Architecture

0 likes · 14 min read

How Xiaohongshu Built an Enterprise AI Personal Assistant from Zero to Full‑Staff Coverage

Xiaohongshu Tech REDtech

Jul 10, 2026 · Artificial Intelligence

PIPO: Pair‑In Pair‑Out Architecture Cuts Input Length in Half and Doubles Token Output for LLMs

The PIPO (Pair‑In, Pair‑Out) architecture compresses two input tokens into one latent vector and expands each hidden state to emit an extra draft token, halving effective input length and doubling per‑step output, achieving up to +7.15 pass@4 improvement and 2.64× TTFT / 2.07× TPOT speedups on benchmarks such as AIME 2025, GPQA‑Diamond, LiveCodeBench v6 and LongBench v2 with Qwen3.5‑4B/9B backbones.

Multi-Token PredictionSpeculative Decodingefficiency

0 likes · 14 min read

PIPO: Pair‑In Pair‑Out Architecture Cuts Input Length in Half and Doubles Token Output for LLMs

Xiaohongshu Tech REDtech

Jun 24, 2026 · Artificial Intelligence

Scaling Enterprise AI Agents: Self‑GC Context Governance and NEX Sandbox

The AICon 2026 talks detail how Xiaohongshu’s engineering team tackles long‑context agent challenges by introducing Self‑GC’s ContextObject model, side‑channel commit mechanisms, a NEX sandbox for runtime isolation, and an L0‑L2 memory hierarchy, achieving 10‑20% token savings with over 90% impact‑free execution.

AI AgentsNEX sandboxSelf‑GC

0 likes · 7 min read

Scaling Enterprise AI Agents: Self‑GC Context Governance and NEX Sandbox

Xiaohongshu Tech REDtech

Jun 23, 2026 · Artificial Intelligence

How AI Agents Can Slash Server‑Side End‑to‑End Test Costs

The article analyzes why server‑side end‑to‑end testing has become costly due to cross‑domain complexity, long chains, and combinatorial explosion, and demonstrates how an AI‑driven agent with dynamic planning, progressive knowledge‑base loading, and a debug‑first script generation loop can dramatically reduce automation effort from days to minutes.

AI AgentDebug-firstDynamic Planning

0 likes · 17 min read

How AI Agents Can Slash Server‑Side End‑to‑End Test Costs

Xiaohongshu Tech REDtech

Jun 17, 2026 · Artificial Intelligence

RedParrot’s Semantic Cache Accelerates Enterprise NL‑to‑DSL Analytics by 3.6×

RedParrot introduces a query‑semantic‑caching framework that compresses the multi‑stage LLM NL‑to‑DSL workflow into a short‑chain process, achieving an average 3.6× inference speedup and an 8.26% accuracy gain on real‑world business data while also delivering strong generalization on open NL‑to‑DSL benchmarks.

Business AnalyticsLLMNL-to-DSL

0 likes · 19 min read

RedParrot’s Semantic Cache Accelerates Enterprise NL‑to‑DSL Analytics by 3.6×

Xiaohongshu Tech REDtech

May 27, 2026 · Cloud Native

How RedProcess Evolved into DES: Optimizing Xiaohongshu’s Multimedia Task Scheduler

The article details the evolution from the first‑generation RedProcess scheduler to the Distributed Execution Scheduler (DES), explaining how architectural redesigns in storage layering, push‑based dispatch, and systematic disaster‑recovery transformed Xiaohongshu’s video‑cloud task scheduling from merely usable to highly efficient and resilient.

DESKubernetesTask Scheduling

0 likes · 15 min read

How RedProcess Evolved into DES: Optimizing Xiaohongshu’s Multimedia Task Scheduler

Xiaohongshu Tech REDtech

May 19, 2026 · Artificial Intelligence

Agent‑Driven R&D Efficiency: Exploration and Practice at QECon Shenzhen 2026

At QECon Shenzhen 2026, Xiaohongshu's tech team will present five technical talks that showcase how AI agents are applied to architecture risk analysis, change automation, large‑model load‑testing data construction, end‑to‑end testing, and client‑side performance, illustrating concrete engineering solutions and measurable productivity gains.

AI AgentAutomationData Pipeline

0 likes · 13 min read

Agent‑Driven R&D Efficiency: Exploration and Practice at QECon Shenzhen 2026

Xiaohongshu Tech REDtech

May 18, 2026 · Artificial Intelligence

CCD‑Aware Thread Orchestration Shatters Multi‑Core CPU Vector Search Performance Ceiling

The paper presents a CCD‑level load‑aware thread orchestration framework that boosts vector ANNS throughput up to 3.7×, cuts P999 tail latency by 30%‑90%, reduces L3 cache miss rates by 6%‑30% and CPU stall time by 20%‑80% on AMD EPYC multi‑chiplet CPUs.

ANNSCCDCPU cache

0 likes · 19 min read

CCD‑Aware Thread Orchestration Shatters Multi‑Core CPU Vector Search Performance Ceiling

Xiaohongshu Tech REDtech

May 12, 2026 · Artificial Intelligence

Treating Automated Testing as AI Coding: Xiaohongshu GUI Agent Real‑World Review

During the 2026 Spring Festival promotion, Xiaohongshu replaced manual UI testing with a three‑layer AI‑driven GUI Agent that executed over 43,000 runs across 106 devices and 128 scenarios, achieving 58% automation, 82% AI‑generated case adoption, 68% bug recall, 98% stability and roughly $1 per test case while drastically cutting token costs.

AI codingCode-as-ActionCost Optimization

0 likes · 23 min read

Treating Automated Testing as AI Coding: Xiaohongshu GUI Agent Real‑World Review