#LLM inference bottleneck
571 related articles
Tutorials·2 min
Tutorial: Deploying a PD-Disaggregated SGLang Multi-Node Inference Cluster on AMD GPUs
Learn how to deploy a PD-disaggregated SGLang inference cluster on AMD GPUs using a single config file, boosting LLM throughput and latency performance.
Read more →
Tech Frontiers·2 min
Step 3.7 Flash: Deep Dive into the 198B Sparse MoE Multimodal Model
Deep dive into StepFun AI's Step 3.7 Flash, a 198B sparse MoE vision-language model with 256K context and 3-level reasoning, excelling in multimodal understanding, AI coding, and Agent tool orchestration.
Read more →
Tech Frontiers·2 min
LFM2.5-8B-A1B: A MoE Model with 1.5B Active Parameters Delivering 4x Its Weight Class Performance
Liquid AI releases LFM2.5-8B-A1B, a MoE model with 8B total params but only 1.5B active, matching 6B-class models in tool calling. Supports 128K context, local deployment, multilingual, with SGLang Day-0 support.
Read more →
Industry Insights·2 min
AMD MI355X Beats B200: Full-Stack Optimization Breakdown for 5% Lower TCO on DeepSeek-R1 Inference
AMD Instinct MI355X achieves 5% lower TCO than NVIDIA B200 on DeepSeek-R1 disaggregated inference via SGLang+MoRI full-stack optimization with 1.25x per-GPU throughput.
Read more →
Tech Frontiers·2 min
Meta Muse Spark Released: A Comprehensive Analysis of the Native Multimodal Reasoning Model
Meta Superintelligence Labs releases Muse Spark, a native multimodal reasoning model supporting visual chain of thought, tool-use, and multi-agent orchestration. Deep dive into its capabilities and competitive positioning.
Read more →
Tutorials·3 min
Cursor Multi-Agent Workflow: A Practical Guide to Main Thread & Grunt Collaboration
Learn the Cursor "Main Thread & Grunt" multi-agent workflow: use a high-tier model for complex tasks and a low-tier model for simple tasks in parallel to maximize AI coding efficiency.
Read more →
Deep Dives·3 min
Single-Agent vs Multi-Agent: A Three-Step Decision Framework for Choosing the Right Architecture
Based on Anthropic's engineering practices, a detailed three-step decision framework for single-agent vs multi-agent architecture: bottleneck identification, technical feasibility, and business value filtering.
Read more →
Tutorials·3 min
SubAgent Architecture: The Core Implementation for Context Isolation
Deep dive into SubAgent context isolation architecture, covering parent-child Agent roles, tool definitions, run_subagent implementation, and differences from TodoList and Agent Teams.
Read more →
Deep Dives·3 min
Claude Sub-agents vs Agent Teams: How to Choose Between Two AI Multi-Agent Collaboration Patterns
Deep comparison of Claude sub-agents vs agent teams: architecture differences, use cases, and real-world results. A Pokémon RPG case study shows how agent teams achieve 95%+ feature completeness.
Read more →
Tutorials·2 min
Claude Code Sub-Agent: A Practical Guide to Multi-Agent Collaboration for Enhanced Development Efficiency
Deep dive into Claude Code Sub-Agent mechanism with a practical blog writing + Git commit case study, showing how multi-agent collaboration solves instruction loss and context bloat issues.
Read more →
Tech Frontiers·3 min
xAI Merges with SpaceX, GPT-5.5-Cyber Preview, Gemini 3.1 Flash Released
Musk announces xAI-SpaceX merger as SpaceX AI, OpenAI launches GPT-5.5-Cyber security model, Google releases Gemini 3.1 Flash, and Airbnb reveals AI writes 60% of new code.
Read more →
Tutorials·3 min
Open-Source Multi-Agent Intelligent Diagnostic System: Deep Dive into MCP + RAG + Skill Routing Architecture
Deep dive into an open-source multi-Agent diagnostic system built on modified OneCall, featuring MCP real-time interaction, RAG-enhanced Q&A, and Skill routing to minimize Token consumption.
Read more →
Tutorials·2 min
The Three-Layer Pyramid Model for Agent Development: From Beginner to Industrial-Grade Deployment
Deep dive into the Three-Layer Pyramid Model for Agent development, covering autonomous agents, collaborative multi-agent systems, and universal orchestration agents with a complete learning path from beginner to industrial-grade deployment.
Read more →
Tutorials·3 min
Deep Agents: Enterprise-Grade Agent Engineering and Deep Research Implementation Guide
Learn how the Deep Agents framework solves enterprise AI Agent challenges like tool sprawl and context pollution, with a complete Deep Research implementation guide covering task decomposition, multi-source integration, and structured report generation.
Read more →
Product Reviews·3 min
Local Deployment of Qwen 3.6 27B on 4×3080Ti: Real-World Coding Test with OpenCode
Real-world test of Qwen 3.6 27B FP8 deployed on 4×3080Ti 16GB modded GPUs with OpenCode for system tool development. Covers hardware setup, inference speed, context management, and productivity gains.
Read more →
Product Reviews·2 min
AI Coding Appliance vs Cloud LLMs: Can ¥480K in Annual Fees Buy 4 Local Deployment Solutions?
A deep cost comparison between AI coding appliances and cloud LLM APIs. A 20-person team spending ¥480K/year on tokens can deploy 4 local OnePanel units at ¥99K each, breaking even in 2.5 months.
Read more →
Product Reviews·3 min
Three AI Agents Tested Head-to-Head: Which One Handles E-Commerce Livestream Data Analysis Best?
Testing three AI Agents on e-commerce livestream data analysis: local deployment memory limits, costly overseas APIs, and how a cloud-based multi-model solution delivers a complete business workflow.
Read more →
Tutorials·2 min
Hermes Agent Practical Guide: From Installation to Feishu Integration
Guide to Hermes Agent's architecture, installation, Skill extensions, Feishu integration, news bots, Python SDK integration, and automated workflows.
Read more →
Tech Frontiers·1 min
Devin Launches Multi-Instance Parallel Mode: AI Programming Evolves from Solo Operations to Army-Scale Collaboration
Devin launches multi-instance parallel mode, letting developers dispatch multiple AI Agents for different tasks simultaneously. Analysis of its impact on development efficiency and how multi-Agent collaboration redefines the developer role.
Read more →
Tutorials·2 min
The Foundation of Agent Platforms: Practical Guide to Session Event Abstraction, Transport, and Storage
Practical guide to Session Event engineering in production Agent platforms: Universal Event abstraction, three-party streaming transport with fault tolerance, and PostgreSQL storage evolution.
Read more →