#token utilization
331 related articles
Product Reviews·2 min
Cursor Composer 2.5 Hands-On: An AI Coding Model That's Faster and 10x Cheaper
Hands-on review of Cursor Composer 2.5's Agent view, Plan mode, and right panel features. Coding ability matches Claude and GPT top models at up to 10x lower cost with significantly faster speed.
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
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 →
Industry Insights·3 min
Deep Dive into Three Major LLM Career Paths: Requirements, Tech Stacks, and Career Prospects
Deep analysis of three core LLM roles—Application Engineer, Development Engineer, and Algorithm Engineer—covering technical requirements, salary thresholds, and career prospects including RAG, fine-tuning, and inference deployment.
Read more →
Tutorials·3 min
DeepSeek V4 Flash MTP Speculative Decoding Real-World Test: A Guide to 20% Faster Local Inference
Real-world testing of DeepSeek V4 Flash with MTP speculative decoding: ~20% speedup for code generation, minimal gains for text. Covers memory overhead, accuracy differences, Q4 vs Q3 quantization, and full deployment tutorial.
Read more →
Product Reviews·2 min
Claude Opus 4.8 Deep Dive: A Comprehensive Review of Judgment, Honesty, and Cost-Effectiveness
Deep dive into Claude Opus 4.8's core upgrades: improved judgment, optimized honest feedback, and Fast Mode costs cut to one-third. Compared with DeepSeek and GPT-5.5 for AI coding and long-context reasoning.
Read more →
Tech Frontiers·3 min
June AI Showdown: Mythos, Sonnet 4.8, and GPT-5.6 All Revealed
June 2025 becomes AI's densest release month: Anthropic Mythos nears launch, Claude Sonnet/Opus 4.8 skip-level upgrades, GPT-5.6 rapid iteration, DeepSeek V4 Pro permanent 75% price cut.
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 →
Tech Frontiers·1 min
DeepSeek V4-Pro Permanent Price Cut: Lower Developer Costs as LLM Price War Heats Up
DeepSeek announces permanent discount pricing for its V4-Pro model. Learn how this impacts developers, V4-Pro's competitive edge, and the latest LLM price war trends.
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 →
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 →
Research·3 min
Inside Cursor Composer 2 Training: A Complete Breakdown of Its Distributed Reinforcement Learning Architecture
Deep dive into how Cursor trained Composer 2 on Fireworks: async pipeline architecture, MoE numerical precision challenges, Router Replay, and global distributed GPU coordination.
Read more →
Research·2 min
Technical Breakdown of Cursor Composer 2's Distributed RL Training
Deep dive into how Cursor trained Composer 2 via distributed RL, covering async pipelines, MoE numerical alignment, global weight sync, and more.
Read more →
Product Reviews·3 min
One API: A Complete Guide to the Open-Source API Gateway for Unified Management of 30+ LLMs
One API is an open-source LLM API gateway with 32K+ GitHub Stars, supporting unified access to 30+ models including OpenAI, Claude, and DeepSeek. Complete guide covering Docker deployment, Key management, and load balancing.
Read more →
Product Reviews·2 min
GLM 5.1 Flagship Model Tested at 400 TPS — From Sketch to Complete App in Two Minutes
Testing Zhipu's GLM 5.1 High Speed API: a full-power flagship model at 400 Token/s. From sketch restoration to generating a complete puzzle game, verifying speed and capability combined.
Read more →
Tutorials·2 min
Claude Code Chinese Manual: A Comprehensive Tutorial from Installation to Practice
A Chinese practical manual for Claude Code on ByteDance's Feishu, covering installation, domestic LLM adaptation, multi-scenario usage tips for zero-barrier AI programming tool adoption.
Read more →
Product Reviews·3 min
GlowIsland: A Productivity Powerhouse That Turns Your Mac's Notch into a Functional Toolbar
GlowIsland turns your Mac's notch into an interactive toolbar with quick notes, music controls, clipboard history, and system tools for a seamless productivity experience.
Read more →
Tech Frontiers·1 min
Go 1.26 Officially Released: New GC, SIMD Support, and Other Major Updates Explained
Go 1.26 officially released with a new garbage collector, significantly reduced cgo overhead, experimental SIMD support, and runtime/secret key management package.
Read more →
Product Reviews·2 min
Claude Code v2.1.141 Update Analysis: From AI Coding Tool to Engineering Workbench
Deep analysis of Claude Code v2.1.141 updates covering notification feedback, plugin HTTPS install, workspace isolation, and CWD filtering—revealing the shift from model competition to engineering experience.
Read more →