#compute optimization
1513 related articles
Tutorials·3 min
Can You Really Transition to AI/LLM in Three Months? A Deep Dive into the Learning Roadmap
Deep dive into a popular 3-month AI/LLM transition roadmap: from Python basics and Prompt engineering to LangChain, RAG, Agents, and hands-on projects, with realistic time estimates and pitfall warnings.
Read more →
Product Reviews·3 min
Mavis Hands-On Review: Multi-Agent Collaboration vs. Single Agent — A Comprehensive Comparison in Academic Research and Web Development
In-depth review of Mavis multi-agent platform across academic retrieval, literature review, and web development. Multi-agent mode significantly outperforms single agents in accuracy and reliability.
Read more →
Tutorials·3 min
Hermes Agent in Practice: A Complete Breakdown from ReAct Loop to Autonomous Skill Evolution
Deep dive into Hermes Agent's four progressive cases: terminal ReAct loop, Feishu AI assistant, four-layer persistent memory, and three-stage Skill evolution with DeepSeek support.
Read more →
Tech Frontiers·3 min
Claude Code Source Code Leak: Full Roadmap for Opus 4.7 and Mythos 5 Exposed
Anthropic suffers a major code leak exposing 500K+ lines of Claude Code source, unreleased Opus 4.7, Sonnet 4.8, Mythos 5 models, 44 hidden feature flags, and the full product roadmap.
Read more →
Product Reviews·3 min
The AI Website Building Era: Do Businesses Still Need Technical Teams?
AI website builders let businesses launch sites without technical teams, but complex needs still require professional development. This article analyzes use cases, limitations, and decision-making advice.
Read more →
Tech Frontiers·3 min
DeepSeek TUI: A Terminal AI Coding Assistant Built in Rust with 2.3K GitHub Stars
DeepSeek TUI is an open-source terminal AI coding tool written in Rust, optimized for DeepSeek API, dubbed Claude Code for DeepSeek. Plus: AI joint ventures, Sierra's $950M raise, and AWS Agent infrastructure updates.
Read more →
Industry Insights·4 min
Qoder's Context Engineering in Practice: Four-Layer Retrieval Engine and Memory System Architecture
Deep analysis of Qoder's (Tongyi Lingma international edition) context engineering architecture, including its four-layer retrieval engine, memory engine, context caching, and core product design.
Read more →
Product Reviews·3 min
Ruflo: A Multi-Agent Orchestration Solution That Turns Claude Code into a 100-Person AI Team
Ruflo is an open-source multi-agent orchestration platform that upgrades single-threaded Claude Code into a distributed AI dev team with 100+ specialized Agents and a SANA self-learning engine.
Read more →
Industry Insights·3 min
Should Custom Software Teams Go All-In on LLMs? ChatGPT Itself Gave the Answer
Should custom software teams go all-in on LLMs? Through a deep conversation with ChatGPT, we analyze scenario selection, Token costs, and industry fit to provide a rational decision framework for ToB developers.
Read more →
Tech Frontiers·2 min
Google Gemini Drops Update: New Interface Design and Spark Intelligent Agent Assistant Explained
Google Gemini Drops brings a complete interface redesign and Gemini Spark 24/7 intelligent agent assistant. Deep analysis of the upgraded experience, agentic AI capabilities, and competition with ChatGPT and Copilot.
Read more →
Tutorials·3 min
35 Lines of Prompts Let Codex Auto-Optimize Your Workflow — Reposted by OpenAI's President
An OpenAI employee used just 35 lines of prompts to have Codex analyze 30 days of work history, identify repetitive tasks, and generate reusable automated Skills. Combined with screen reading and long-term memory, Codex is becoming a proactive workflow optimization agent.
Read more →
Product Reviews·3 min
Codex Computer Use Hands-On Review: Setup Guide, How It Works, and Security Risks Explained
Hands-on review of OpenAI Codex Computer Use: step-by-step setup guide, WeChat demo, screenshot-based core principles, and analysis of three major security risks including privacy leakage and current limitations.
Read more →
Tech Frontiers·1 min
Windsurf Integrates Claude Opus 4.7 Fast Mode with 2.5x Speed Boost
Windsurf integrates Claude Opus 4.7 fast mode with 2.5x speed boost while retaining full intelligence. Analysis of its impact on developer productivity and AI coding tool competition.
Read more →
Research·2 min
Agent Loops in Practice: Transforming Token Output into Productivity from CUDA Kernels to Automated Research
Deep dive into how the Humanize framework transforms LLM tokens into engineering productivity via Agent Loops. Covers KDA winning CUDA kernel contests, virtual hardware optimization, and 50% research cost reduction.
Read more →
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
SGLang v0.5.12.post1 Released: DeepSeek V4 Stability Fixes and Blackwell Adaptation
SGLang v0.5.12.post1 stability patch details: 12 critical fixes covering DeepSeek V4 garbled text and crashes, NIXL PD disaggregated inference logic, Blackwell B300 adaptation, and cold start optimization.
Read more →
Industry Insights·2 min
SGLang Enters Finance: How AI Inference Infrastructure Is Reshaping Wall Street
SGLang co-hosts a finance AI inference event with Crusoe AI and Cloudflare, exploring LLM inference deployment in trading, risk management, and compliance — signaling Wall Street's shift to production-grade AI infrastructure.
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·1 min
Cloudflare Contributes Critical KV Cache and Mooncake Fixes to SGLang
Cloudflare contributes decode KV cache offload and Mooncake recovery fixes to SGLang, resolving garbled output under high concurrency for Kimi K2.6 and enabling automatic fault recovery in distributed inference.
Read more →
Tech Frontiers·1 min
SGLang Hosts Agent Loops Office Hour, Focusing on Agentic Loop Architecture Optimization
SGLang team hosts an Agent Loops Office Hour exploring inference optimization for agentic loops, covering KV Cache reuse, low-latency multi-turn dialogue, and tool calling techniques.
Read more →