WeSearch
Hub / Tags / Cache
TAG · #CACHE

Cache coverage.

Every story in the WeSearch catalog tagged with #cache, chronological, with view counts. Subscribe to the per-tag RSS feed to follow this topic in your reader of choice.

60 stories tagged with #cache, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.

⌘ RSS feed for this tag →   or   search "Cache"

RELATED TAGS
#cicd2#buildcache2#optimization2#intel1#says1#software1#more1#devops1#softwaredevelopment1#developerproductivity1#docker1#ml1
ARXIV.ORG

KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

arXiv:2607.09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly…

21 views ·
#kv-prm#efficient#process
GITHUB

Same agent tasks, 76% fewer LLM calls – we moved semantic cache inside the graph

Deterministic AI agent orchestration — comment via Discussions & Issues; code changes by maintainers only. - insightitsGit/ChorusGraph…

22 views ·
#same#agent#tasks
FOX NEWS

Archaeologists unearth ancient treasure cache at biblical city connected to Genesis

Archaeologists have uncovered ancient treasure at Heliopolis, the biblical city mentioned in the story of Joseph, including possible gold earrings and scarabs.…

29 views ·
#archaeologists#unearth#ancient
ARXIV.ORG

Still: Amortized KV Cache Compaction in a Single Forward Pass

The KV cache is the memory bottleneck of long-horizon language model deployment. Practically, a deployable compactor must be lightweight enough to call during inference, expressive…

31 views ·
#machine‑learning#natural‑language‑processing#model‑compression
THE JERUSALEM POST | JPOST.COM

Iran booby traps entrances, collapses tunnels leading to cache of enriched uranium - report

This comes a day after a senior administration official told reporters that the US and Iran are close to a deal requiring Iran to relinquish its uranium, which has been enriched to…

29 views ·
#nuclear#iran#diplomacy
GITHUB

CI caching is not one cache

Where native caches win, where Incredibuild's proprietary compiler cache wins, and how disposable Islo runners change the CI cache problem.…

29 views ·
#ci#caching#development
BETTERDB PLAYGROUND

Show HN: Self tuning chat exposing it's semantic and agentic cache

Open-source RAG chatbot over Valkey, Redis OSS, Dragonfly, and BetterDB docs. Live demo of @betterdb/agent-cache and @betterdb/semantic-cache with real-time hit/miss metrics.…

31 views ·
#technology#databases#caching
R/AWS

Users bounce after 2 minutes, but CDN caches the whole 5GB movie. How to stop wasting bandwidth?

45 views ·
R/STABLEDIFFUSION

AutoCachedPreview

28 views ·
DEV.TO (TOP)

Scarab Diagnostic Suite Field Test #005: A Terraform Core Cache Boundary

This is the fifth field test in my Scarab Diagnostic Suite series, and it is the most significant one...…

32 views ·
#terraform#diagnostics#devops
DEV.TO (TOP)

Great Stack to Doesn't Work #3 — Redis: "99% Cache Hit Ratio, System Down"

A survival guide for when everything goes wrong in production. Your Redis dashboard looks...…

23 views ·
#redis#backend#devops
R/MACOS

Wondered why my storage was horrible. Meanwhile, my cache.

30 views ·
R/MACHINELEARNING

Event like spiking neuron lib that fits into the CPU cache [P]

29 views ·
R/PROGRAMMING

Agent Memory Is a Cache Coherence Problem

38 views ·
TECHMEME

Xcena, whose MX1 chip performs data orchestration and KV cache management directly within memory modules, raised a $135M Series B at a $570M valuation (Kate Park/TechCrunch)

26 views ·
TOM'S HARDWARE

New Silicon Motion SM2524XT chip brings 14 GB/s to mainstream SSDs — 6nm DRAMless controller boasts heavy AI PC optimization and slashes KV cache latency

Fast, furious, inexpensive.…

31 views ·
#technology#ssd#ai
DEV.TO (TOP)

KV-Pool: 4.5x Agent Inference Throughput with Persistent KV Cache

Why Agent Workloads Are Expensive LLM inference costs always scale with context length. In...…

21 views ·
#ai#technology#cloud
BOING BOING

LAPD discovers huge fireworks cache, raising fears of another LAPD fireworks disaster

Los Angeles residents were evacuated Wednesday after police discovered a massive cache of illegal fireworks inside a South LA home. Such a development would be alarming in any urba…

29 views ·
#fireworks#safety#law enforcement
PHORONIX

Cache Aware Scheduling Shows Nice Wins For AMD Zen 5 On PostgreSQL, Valkey, Network Performance

The long-in-development work on Cache Aware Scheduling looks like it will come to a head soon with it looking like Cache Aware Scheduling will land for Linux 7.2.…

43 views ·
#aware#scheduling
DEV.TO (TOP)

The One Cache That Broke Our Treasure Hunt Engine

The Problem We Were Actually Solving Our core game loop was: player scans QR → API writes...…

28 views ·
#webdev#programming#architecture
DEV.TO (TOP)

The Day Treasure Hunt Broke My Caches—And How We Fixed It

The Problem We Were Actually Solving The treasure hunt engine used a single Redis sorted...…

34 views ·
#webdev#programming#architecture
DEV.TO (TOP)

The Cache That Bled — How We Turned Veltrix Event Config From Silent Killer to Silent Savior

The Problem We Were Actually Solving We assumed Postgres could keep up with event...…

24 views ·
#webdev#programming#architecture
DEV.TO (TOP)

Edge-Cached Localhost Tunnels: How to Give Stakeholders a Production-Fast Preview Directly from Your IDE

IT InstaTunnel Team Published by our engineering team Edge-Cached Localhost Tunnels: How to Give...…

25 views ·
#webdev#performance#tooling
R/CYBERSECURITY

GitHub Actions Cache Poisoning is eating open source

34 views ·
YCOMBINATOR

Show HN: MurrDB: A RocksDB-based NVMe/S3 cache for AI inference workloads

25 views ·
R/LOCALLLAMA

Shard - getting to 10× KV cache compression

26 views ·
PHORONIX

Meta's CacheLib Sees New Release After Two Year Hiatus For Helping With High DRAM Prices

Back in 2021 Facebook open-sourced CacheLib as a new caching engine…

32 views ·
#technology#software#meta
R/LOCALLLAMA

(Yet Another) KV cache calculator - kvanta.vcerny.cz

21 views ·
ZHUOHAN'S HOMEPAGE

PEEK: Give Your Agent an Orientation Cache (MIT CSAIL, Khattab group)

We introduce PEEK, a system that caches reusable orientation knowledge about a recurring external context as a small, prompt-resident context map.…

20 views ·
#artificial intelligence#machine learning#language models
R/LOCALLLAMA

OSCAR RotationZoo - Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

27 views ·
R/PROGRAMMING

A selfie crashed Twitter in 20 minutes. Not traffic — a single cache key. Here's what actually happened.

47 views ·
ARXIV CS.AI

ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the …

24 views ·
#computer science#distributed computing#artificial intelligence
ARXIV CS.AI

Tensor Cache: Eviction-conditioned Associative Memory for Transformers

Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the …

26 views ·
#machine learning#artificial intelligence#transformers
KNIGHTLI BLOG

DeepSeek-V4 KV Cache Explained: Why 1M Context Uses Less VRAM

A comparison of DeepSeek-V4's CSA/HCA hybrid compressed attention with traditional MHA, GQA, and MLA, explaining why DeepSeek-V4 can greatly reduce KV Cache memory for 1M-token con…

20 views ·
#ai#technology#machine learning
R/LOCALLLAMA

llama.cpp has a clever trick for speeding up KV cache decode

29 views ·
CACHE

Cache – Meal plans from your local store's weekly sales

Plan weekly dinners around live grocery sales at Kroger, Fred Meyer, Ralphs, and 35+ states. Cache matches meals to this week's deals — saving families $40–60/month.…

13 views ·
GITHUB

TID: Linux kernelmodule–flushes CPU cache after wiping sensitive data CLFLUSHOPT

Hardware-level security protocol for mitigating cache-based side-channel attacks. - ahmaaaaadbntaaaaa-byte/TID-The-Instant-Destroyer…

20 views ·
#security#technology#research
DEV.TO (TOP)

no-cycle finds 0 cycles in next.js (and other lies caches tell you)

Our import-next/no-cycle reported 0 cycles in next.js's 14K-file repo. oxlint reported 17. The same rule, run on a 33-file subset of the same repo, found 5+. The bug: cache polluti…

26 views ·
#eslint#staticanalysis#performance
R/CLAUDEAI

Cache miss in Claude Code costs 12.5× more than a hit. Here are 5 things you do mid session that quietly trigger it

25 views ·
R/LOCALLLAMA

Inference provider tiers by Cache-hit rates, using openrouter data

31 views ·
DIRAC

Cache hit rates of Inference are more meaningful than the headline costs

18 views ·
#technology#artificial intelligence#data analysis
YCOMBINATOR

Ask HN: Does anyone what a "RiotCache.dat" file was doing in my EFI partition?

22 views ·
#gaming#technology#software
LWN.NET (LINUX WEEKLY NEWS)

[$] Custom page-cache policies with BPF

The kernel's page cache is charged with maintaining pages (or, more correctly, folios) containi [...]…

34 views ·
#linux#kernel#bpf
R/GOLANG

Go build cache increases to hundreds of GB when running AI agents

35 views ·
GITHUB

Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT

19 views ·
R/NETSEC

GitHub Actions Cache Poisoning is eating open source

27 views ·
R/PROGRAMMING

A performance regression in code I didn’t touch: debugging an L1 i-cache associativity issue

32 views ·
R/SYSADMIN

Custom DHCP Option 235 for Microsoft Connected Cache – Not Being Picked Up by Clients

23 views ·
DEV.TO (TOP)

The Google I/O 2026 announcement that quietly broke my cost spreadsheet: Gemini's cache-discount tier

Google I/O 2026 had the headline stuff. Gemma 4 in four sizes. The new agent-friendly Gemini...…

24 views ·
#googleio#gemini#ai
R/MACOS

The home user folder is taking up 300GB, but its contents add up to 150GB at most. How is this even possible? All ~/Logs, ~/Cache, etc. are clean

19 views ·
PHORONIX

The Very Exciting Cache Aware Scheduling Looks Like It Will Land For Linux 7.2

As a very exciting development ahead of the Linux 7.2 kernel merge window opening in about one month's time, it looks like the long-awaited Cache Aware Scheduling support will fina…

34 views ·
#linux#technology#software
R/SELFHOSTED

Selfhosted second brain app: markdown-based, built-in MCP server, SQLite cache layer and semantic search. Any interest from this community?

23 views ·
R/DEVOPS

Fixed our cache but full builds are still slow as hell

31 views ·
DEV.TO (TOP)

AWS CloudFront Cache Policies: Complete Guide

A CloudFront cache policy controls two things: the cache key (which combination of URL, headers,...…

28 views ·
#aws#cdn#webdev
DEV.TO (TOP)

KV Cache Explained Like You're an LLM Engineer

How transformer inference actually works under the hood — and why KV cache is the single most...…

16 views ·
#ai#llm#machinelearning
ARXIV CS.AI

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approach…

18 views ·
#artificial intelligence#machine learning#long-context
DEV.TO (TOP)

Stop Hardcoding AI Prompts: A Developer’s Guide to PromptCache

Manage, version, and deploy your team’s AI prompts like code — with a TypeScript SDK, REST API, and...…

24 views ·
#ai#development#tooling
THE FIRETIGER BLOG

Agentically optimizing LLM prompt cache TTLs for fun and profit

A case study on production objective hill climbing Firetiger runs a few hundred large language model (LLM) agents in production, and prompt caching is a critical tool to manage th…

33 views ·
#technology#artificial intelligence#cost optimization
GOOGLE NEWS

OpenAI's ChatGPT Has A Web Cache - Search Engine Roundtable

Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…

27 views ·
HACKER NEWS (NEWEST)

Blog post: why and how we built local-first with Zero (prev. Replicache)

22 views ·