cache management
30 articles about cache management in AI news
LMCache Splits KV Cache From Inference, 14x Faster TTFT on H200s
LMCache separates KV cache management from inference into a dedicated process, achieving 14x faster TTFT on H200s with Qwen3-235B at 50 concurrent users.
KV Cache Offload Makes Storage the New AI Bottleneck
Storage, driven by KV cache offload and rising SSD costs, is now the primary AI bottleneck per Supermicro and SemiAnalysis.
CacheBlend: 2-4x Faster KV Cache for Multi-Doc Queries
CacheBlend reuses per-document KV caches by recomputing only boundary tokens, achieving 2-4x speedups on multi-document queries. Alibaba data shows 10% of blocks serve 77% of hits.
MLX-VLM Adds Continuous Batching, OpenAI API, and Vision Cache for Apple Silicon
The next release of MLX-VLM will introduce continuous batching, an OpenAI-compatible API, and vision feature caching for multimodal models running locally on Apple Silicon. These optimizations promise up to 228x speedups on cache hits for models like Gemma4.
Anthropic's Silent Cache TTL Cut
Claude Code's default cache TTL was silently reduced to 5 minutes on April 2, drastically increasing token costs. Use hooks and settings to mitigate the impact.
Microsoft's 'Compress-Thought' Cuts KV Cache 2-3x, Boosts Throughput 2x
A new Microsoft paper shows language models can learn to compress their reasoning steps on-the-fly, slashing memory use 2-3x and doubling throughput. Crucially, 15 percentage points of accuracy come from 'leaked' information in KV cache after explicit reasoning is erased.
arXiv Survey Maps KV Cache Optimization Landscape: 5 Strategies for Million-Token LLM Inference
A comprehensive arXiv review categorizes five principal KV cache optimization techniques—eviction, compression, hybrid memory, novel attention, and combinations—to address the linear memory scaling bottleneck in long-context LLM inference. The analysis finds no single dominant solution, with optimal strategy depending on context length, hardware, and workload.
Neural Paging: The Memory Management Breakthrough for Next-Gen AI Agents
Researchers propose Neural Paging, a hierarchical architecture that decouples symbolic reasoning from information management in AI agents. This approach dramatically reduces computational complexity for long-horizon reasoning tasks, moving from quadratic to linear scaling with context window size.
DualPath Architecture Shatters KV-Cache Bottleneck, Doubling LLM Throughput for AI Agents
Researchers have developed DualPath, a novel architecture that eliminates the KV-cache storage bottleneck in agentic LLM inference. By implementing dual-path loading with RDMA transfers, the system achieves nearly 2× throughput improvements for both offline and online scenarios.
Prism v1.8 Adds CLI, MCP Server, and SDKs — Here's How to Use Them with
Prism v1.8's MCP server gives Claude Code direct control over caches, budgets, and routing. Install it in 2 minutes and ditch the dashboard for terminal-based AI infrastructure management.
Claude Code Digest — May 01–May 04
CCmeter's cache-busting insights can slash your Claude Code costs by up to 40% instantly.
Claude Code Digest — Apr 28–May 01
CCmeter's cache-busting insights can cut your Claude Code costs by up to 40% instantly.
ML-Master 2.0 Hits 56.44% on MLE-Bench in 24-Hour Agentic Science Run
Researchers from Shanghai Jiao Tong University demonstrated ML-Master 2.0, an autonomous research agent that operated continuously for 24 hours on the MLE-Bench, achieving a 56.44% medal rate. The breakthrough centers on Hierarchical Cognitive Caching for state management, not reasoning, enabling long-horizon scientific workflows.
Atomic Chat's TurboQuant Enables Gemma 4 Local Inference on 16GB MacBook Air
Atomic Chat's new TurboQuant algorithm aggressively compresses the KV cache, allowing models requiring 32GB+ RAM to run on 16GB MacBook Airs at 25 tokens/sec, advancing local AI deployment.
Forge: The Open-Source TUI That Turns Claude Code into a Multi-Model Swarm
Forge is a new open-source tool that orchestrates multiple AI coding agents (including Claude Code) using git-native isolation and semantic context management to overcome token limits.
mlx-vlm v0.4.4 Launches with Falcon-Perception 300M, TurboQuant Metal Kernels & 1.9x Decode Speedup
The mlx-vlm library v0.4.4 adds support for TII's Falcon-Perception 300M vision model and introduces TurboQuant Metal kernels, achieving up to 1.9x faster decoding with 89% KV cache savings on Apple Silicon.
Edge Computing in Retail 2026: Examples, Benefits, and a Guide
Shopify outlines the strategic shift toward edge computing in retail, detailing its benefits—real-time personalization, inventory management, and enhanced in-store experiences—and providing a practical implementation guide for 2026.
LeCun's Team Uncovers Hidden Transformer Flaws: How Architectural Artifacts Sabotage AI Efficiency
NYU researchers led by Yann LeCun reveal that Transformer language models contain systematic artifacts—massive activations and attention sinks—that degrade efficiency. These phenomena, stemming from architectural choices rather than fundamental properties, directly impact quantization, pruning, and memory management.
NVIDIA's Memory Compression Breakthrough: How Forgetting Makes LLMs Smarter
NVIDIA researchers have developed Dynamic Memory Sparsification, a technique that compresses LLM working memory by 8× while improving reasoning capabilities. This counterintuitive approach addresses the critical KV cache bottleneck in long-context AI applications.
7 AI Agent Cost Optimization Strategies That Cut LLM Bills by Up to 90%
The source outlines seven cost optimization strategies for AI agents, including prompt compression and model routing, that can reduce LLM bills by up to 90%. This matters for retail and luxury brands deploying AI at scale where inference costs can become prohibitive.
DeepSeek, Zhipu AI Build Custom Inference Chips to Cut GPU Dependency
DeepSeek and Zhipu AI are developing custom inference chips to cut GPU costs. China's domestic chip budget share hit 46% in July 2026.
How Major Retailers Use AI to Reimagine the Customer Journey
BizTech Magazine reports that retailers like Kering and Nike use Google Cloud AI to personalize customer journeys, lifting revenue 10-30%. This matters as AI transforms omnichannel retail with real-time data and generative models.
Stop Hardcoding Model Lists: Use Discovery-Driven MCP to Cut Token Bloat 40%
Switch from hardcoded MCP tool schemas to discovery-driven tools like nvidia_list_foundation_models. Your agent queries available models dynamically, cutting token bloat and adapting to infrastructure changes in real-time.
Claude Code's June 15 Agentic Credit Split: How to Avoid Hitting the $20 Wall
Claude Code's June 15 agentic credit split moves `claude -p` and CI workflows to a separate $20/month bucket on Pro. Upgrade to Max 5x or switch to direct API for production pipelines.
Claude Code's Six-Layer Architecture: Harness, Not Magic
Claude Code's six-layer architecture uses a 3-layer context compressor at 92% threshold and Redis-based multi-agent FSM protocol. The model is just one node in a harness.
How Andre Karpathy's CLAUDE.md Guidelines Save Millions of Tokens — and
Andre Karpathy's CLAUDE.md patterns cut token waste by 40%+. Copy his exact config to slash costs and speed up Claude Code.
The Claude Code Cheat Sheet You Need: 5 Commands That Save Hours
A comprehensive cheat sheet for Claude Code has been released, compiling critical CLI commands, MCP server setups, and workflow shortcuts to eliminate guesswork and speed up development.
Claude Code Digest — Apr 18–Apr 21
Switch to FastMCP for MCP server builds — eliminate copy-paste workflows in 15 minutes.
VMLOps Publishes NLP Engineer System Design Interview Guide
VMLOps has published 'The NLP Engineer's System Design Interview Guide,' a detailed resource covering architecture, scaling, and trade-offs for real-world NLP systems. It provides a structured framework for both interviewers and candidates.
Google, Marvell in Talks to Co-Develop New AI Chips, Including TPU-Optimized MPU
Google is reportedly in talks with Marvell Technology to co-develop two new AI chips: a memory processing unit (MPU) to pair with TPUs and a new, optimized TPU. This move is a direct effort to bolster Google's custom silicon stack and compete with Nvidia's dominance.