Tagged articles
AI Infra
11 articles · Page 1 of 1
JD Retail's Firefly AIGC platform moves beyond single-model generation to scalable content production by unifying orchestration, differentiated execution via Ray Serve and Ray Data, a Lance-based multimodal data lakehouse for material governance, and end-to-end traceability across DAG workflows.
AI InfraAIGCContent Production
0 likes · 22 min read

Search engines are evolving from simple information‑finding tools into AI infrastructure that links enterprise data with AI capabilities, a shift highlighted by a DTCC conference slide and Elastic's AI Search event, and reflected in Elastic 9.5's new columnar mode, vector auto‑calibration, and PromQL support, as well as Easysearch's three‑step strategy for reliable, cost‑effective AI workloads.
AI InfraAI infrastructureEasysearch
0 likes · 5 min read

By decoupling VAE encoding from the main training GPU, redesigning the data flow into a fully asynchronous pipeline, and applying dynamic scheduling, multi‑level caching, and custom operators, the Cosmos3‑Nano‑Policy‑DROID system achieves a 2.1× overall throughput with only 1.5× the hardware cost, delivering roughly 35% more training throughput for the same budget.
AI InfraGPU clusterVAE Encoding
0 likes · 18 min read

A real‑world incident where a tiny Prompt tweak caused a two‑day outage illustrates why AI systems need CI/CD‑style versioning and gated release for six objects—code, Prompt, model, RAG index, tool schema, and workflow—so that changes are traceable, safely rolled out, and quickly reverted.
AI InfraGray ReleaseL7 Evaluation Gate
0 likes · 31 min read

By applying systematic AI Infra engineering—optimizing data loading, I/O pipelines, activation checkpointing, torch.compile, and multi‑node scaling—the Cosmos‑3‑Nano‑Policy‑DROID model achieved an 89× faster startup, 99.3% higher single‑node throughput, 0.42 MFU, and 98.3% scaling efficiency across 12 nodes, all without NVLink.
AI InfraActivation CheckpointingCosmos 3
0 likes · 13 min read

The article analyzes the architectural challenges of large‑model inference in the Agent era—such as memory‑intensive MLA structures, MoE communication overhead, exploding KV‑Cache size, and tool‑call accuracy—and presents a series of engineering solutions including hierarchical KV‑Cache pooling, sequence parallelism, offloading strategies, and chip‑level adaptations to achieve higher throughput and lower token costs.
AI InfraAgentDeepSeek
0 likes · 15 min read

The article details Baidu Baige’s end‑to‑end AI infrastructure for embodied intelligence, covering VLA and world‑model architectures, scaling challenges for medium‑sized models, cloud‑based motion‑control pipelines, open‑source integration, hardware‑aware training optimizations, and simulation‑engine improvements that together speed up model development and deployment.
AI InfraBaidu BaigeEmbodied AI
0 likes · 13 min read

This article explains how Alibaba engineers transformed millions of HSF microservices into MCP servers without code changes by leveraging the Higress AI gateway, detailing the ecosystem components, step‑by‑step migration process, challenges of rapid MCP evolution, and strategic insights for AI infrastructure teams.
AI InfraHSFHigress
0 likes · 8 min read

The article analyzes the AI+ era’s impact on industry digital infrastructure, outlines three major challenges of digital‑to‑intelligent transformation, reviews the evolution of the "Yuanqi" platform from 2022 to 2024, and explains how its four‑platform architecture and AI‑Infra upgrades aim to accelerate sustainable, AI‑driven productivity across sectors.
AIAI InfraCloud Native
0 likes · 14 min read

At the 2024 Yunqi Conference, Alibaba Cloud’s AI Infra experts detailed the latest challenges of large‑model deployment—such as hardware costs, resource management, and software‑hardware coordination—and introduced PAI’s new capabilities, including stability tools, automated distributed training, reinforcement‑learning frameworks, inference optimizations, and integrated big‑data AI solutions.
AI InfraInference Optimizationbig-data-integration
0 likes · 14 min read


AntTechJul 12, 2023 · Artificial Intelligence
This article describes the Hybrid Embedding solution proposed by Ant AI Infra to address storage, resource, and feature‑governance challenges of massive sparse CTR models, detailing its multi‑layer storage design, KV‑based parameter server, and performance gains in large‑scale recommendation systems.
AI InfraCTRHybrid Embedding
0 likes · 9 min read
