Follow us to discover more Baidu tech insights.
An in‑depth guide walks you through installing OpenClaw, understanding its gateway, channel, agent, tool, and skill architecture, managing token costs, creating multi‑agent workflows, securing API keys, and troubleshooting common issues, empowering developers to build scalable AI‑driven automation.
This article analyzes the challenges of scaling ClickHouse within Baidu’s MEG data platform and details a lake‑house solution that decouples storage and compute, integrates a meta‑service for transparent data access, optimizes query performance through caching, data roll‑up and layout tuning, and introduces a unified query gateway that gracefully falls back to Spark for complex workloads.
This article explains why large‑model agents need structured Skills to capture team‑specific knowledge and workflows, describes the evolution from MCP to Skill, details the progressive‑disclosure design, shows how to write, organize, and install Skills, and provides a systematic evaluation and iteration process to ensure high‑quality, token‑efficient agent behavior.
This article recounts how Baidu's storage team tackled the performance and scalability limits of traditional object storage by redesigning metadata handling with the Mantle and MantleX architectures, introducing a centralized IndexNode, strong consistency, delta‑record writes, and a seamless single‑node to distributed transition for massive file systems.
This article outlines the rapid rise of embodied intelligence, the explosion of Vision‑Language‑Action (VLA) research, and how cloud‑based AI infrastructure—including multi‑level IaaS, data pipelines, dual‑system model designs, and reinforcement‑learning workflows—addresses emerging scaling and deployment challenges.
Within two days, Baidu’s Baige and Kunlun Chip teams adapted the 309‑billion‑parameter MiMo Flash V2 model—featuring a hybrid SWA+Sink and Full Attention mechanism—to run efficiently on the Kunlun P800 XPU using the vLLM‑Kunlun Plugin, achieving lossless performance comparable to GPU inference.
The article explains how Baidu’s Baige team integrated a Context Parallelism strategy into DeepSeek V3.2, detailing the DSA architecture, the limitations of traditional tensor and sequence parallelism, and how CP distributes computation and memory across GPUs to achieve up to an 80 % reduction in token‑to‑first‑token latency for ultra‑long 128K‑token contexts.
The vLLM‑Kunlun Plugin, jointly released by Baidu Baige and Kunlun Chip, provides a high‑performance, zero‑intrusion solution for deploying open‑source large language models on domestic Kunlun XPU hardware, includes fused operators, precision‑validation and profiling tools, and supports over twenty mainstream and multimodal models.
This report analyzes the memory bottleneck of DeepSeek‑V3.2‑Exp’s sparse‑attention decoder, proposes the Expanded Sparse Server (ESS) to offload the latent cache to CPU memory, and demonstrates through high‑fidelity simulation that the approach dramatically improves decode throughput while keeping latency within acceptable limits.
This article explains how traditional kernel network stacks struggle with high‑concurrency, low‑latency cloud data‑center workloads and introduces Baidu Intelligent Cloud’s Polar solution—Polar‑TCP and Polar‑RDMA—which combine user‑space DPDK drivers, a lightweight TCP stack, and an industrial RPC framework to achieve near‑RDMA performance while preserving compatibility with existing TCP ecosystems.
