#KV cache
480 related articles
·4 min
From Enter to First Token: Decrypting the Full LLM Inference Pipeline (Autoregression, KV Cache & Decoding Strategies)
From pressing Enter to the first character appearing, what happens inside an LLM? This article breaks down autoregressive generation, KV cache acceleration, and decoding strategies like temperature, Top-k, and Top-p.
Read more →
·4 min
KV Cache Saves 20x on Costs: The Underlying Principles and Practical Tips for LLM Inference Optimization
Deep dive into how KV Cache reduces LLM API costs by 20x. From Transformer attention matrix multiplication overhead to prompt caching best practices, understand the fundamentals of AI inference cost optimization.
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 →
Deep Dives·3 min
Augment Code Architecture Revealed: Dedicated Subagents Replace KV Cache, Cutting Costs by 90%
Deep dive into how Augment Code uses Mercury 2 dedicated subagents to replace traditional KV cache, achieving 82% faster context compaction, 90% lower summarization costs, and 30% reduced LLM spending.
Read more →
·2 min
antirez Strikes Again: ds4, a Pure C Local Inference Engine for DeepSeek 4
Redis creator antirez open-sources ds4, a pure C local inference engine for DeepSeek 4 Flash and PRO with native Metal, CUDA, and ROCm support, earning nearly 20K GitHub stars.
Read more →
·3 min
Training a 1.3B Parameter LLM from Scratch: Complete Workflow and Core Challenges
A deep dive into the complete workflow of training a 1.3B parameter LLM from scratch, covering Transformer architecture design, data preparation, and distributed training optimization.
Read more →
·1 min
Storage-Class Memory Revolution: GPU Memory May Leap to Multi-Terabyte Capacity
Exploring how storage-class memory technology can break through GPU memory bottlenecks, expanding single-card usable memory to multi-terabyte levels through tiered memory architecture.
Read more →
·2 min
GPT-5.6 Luna Price Cut by 80%: A Full Breakdown of OpenAI's Latest Pricing Strategy
OpenAI announces major GPT-5.6 price cuts: Luna down 80%, Terra down 20%, Sol gets faster API options. Full analysis of strategy and developer impact.
Read more →
·3 min
Running the 1.56TB Kimi K3 Model on 8GB RAM with Pure C
A developer built a pure C99 inference engine that runs the 1.56TB Kimi K3 model on 8GB RAM using MoE sparsity and NVMe on-demand loading—no GPU, 176KB binary.
Read more →
·3 min
Building a Local AI Agent Architecture: From Scattered Scripts to Your Personal Jarvis
A practical guide to consolidating scattered automation scripts into a local AI Agent hub. Covers Function Calling, Ollama+Qwen2.5 deployment, tool orchestration architecture, and a complete implementation roadmap.
Read more →
·3 min
MI355X Running Kimi K3 Benchmark: The Logic Behind Outperforming B300 in Performance per Dollar
Deep analysis of AMD MI355X running Kimi K3 with superior cost-efficiency vs NVIDIA B300, and its implications for the AI inference hardware market.
Read more →
·3 min
Persistent State Machines: How INT4 Memory Cells Reshape LLM Attention Mechanisms
Exploring how persistent state machines with INT4-quantized memory cells reshape LLM attention, breaking KV Cache memory bottlenecks for long-context inference on edge devices and high-concurrency scenarios.
Read more →
·3 min
Why Local Agents Crash: A Real-World Report from 4,265 Actual Sessions
A developer spent a month testing 4,265 Claude Code/Codex sessions, revealing why local Agents crash on consumer hardware: tool lists consume 41% of cache, q4_0 quantization traps, and eviction strategy ceilings of only 11.88%.
Read more →
·3 min
Dual RTX 3060 Running DeepSeek V4 Flash: IQ2_M Quantized Inference Benchmarked at 3.5 tok/s
Benchmarking DeepSeek V4 Flash on dual RTX 3060 GPUs with 96GB RAM at IQ2_M quantization achieving 3.5 tokens/sec. Covers hardware choices, 2-bit quantization techniques, and local LLM deployment optimization.
Read more →
·3 min
Warpgate 0.27 Released: Open-Source Bastion Host Adds RDP/VNC and Cluster Support
Warpgate 0.27 adds transparent RDP/VNC proxy, OTP/SSO integration, cluster scaling, and TLS hot-reload. A FOSS alternative to Teleport requiring no agents or clients for unified privileged access.
Read more →
·2 min
Running Local LLMs on a 24GB Mac Mini: Model Selection & Speed Optimization Guide
24GB Mac Mini too slow for local LLMs? Learn why 14B models struggle, get 3B-8B model recommendations for Home Assistant, and discover Ollama speed optimization tips.
Read more →
·6 min
AI Coding Boosts Productivity 10x: Are Programmers Writing Their Own Pink Slips?
A senior developer admits 95% of work is done by Claude Code, with 10x productivity gains. From coding to architecture, AI is eroding programmers' core skill moats. Deep analysis of AI coding's impact on tech employment.
Read more →
·3 min
How Cheap Can It Be to Serve a 2.8 Trillion Parameter Model? A Deep Dive into Inference Economics
Deep analysis of the real cost of serving a 2.8 trillion parameter model. From MoE sparse activation to batching scale effects and inference optimization, revealing why model size and serving cost are less correlated than assumed.
Read more →
·1 min
Predictive KV Replication: Breaking Through the Bursty Traffic Bottleneck in LLM Inference
Deep dive into predictive speculative KV replication: how anticipating bursty traffic and pre-replicating KV Cache can reduce LLM inference tail latency.
Read more →
·3 min
Practical Guide to Setting Up a Local AI Coding Environment on MacBook Pro M4
Complete guide to setting up a local AI coding environment on MacBook Pro M4, covering Ollama, MLX, Continue, Qwen3-Coder 30B configuration, and performance optimization strategies for 32GB RAM.
Read more →