Memory optimization

18 posts · 13 sources

+5

Two Minute PapersYouTube1d

DeepSeek Solved AI’s Memory Problem

QdrantBlog1w

How Small Can Google's New EmbeddingGemma 2 Get?

Jane StreetBlog1w

Trading off compute for memory with activation checkpointing

CloudflareBlog3w

Saving another 100TB of RAM with math (and Rust)

RampBlog22 Jul

Apache Arrow Cut Snowflake Fetch Memory Growth by Up to 79%

MilvusBlog3 Jun

How to Run 25 Million Image Vectors on Under 1GB of Memory in Milvus

NVIDIABlog2 Jun

Deploy Agentic-Ready AI at the Edge with Memory Efficiency in NVIDIA JetPack 7.2

MilvusBlog2 Apr

Beyond the TurboQuant-RaBitQ Debate: Why Vector Quantization Matters for AI Infrastructure Costs

MilvusBlog10 Dec

Introducing AISAQ in Milvus: Billion-Scale Vector Search Just Got 3,200× Cheaper on Memory

ExaBlog5 May

Optimizing BM25 for the Next Generation of Semantic Search Technology

GrabBlog30 Oct

How we reduced peak memory and CPU usage of the product configuration management SDK

CloudflareBlog31 Mar

Upgrading one of the oldest components in Cloudflare’s software stack

GitLabBlog8 Jul

How we migrated application servers from Unicorn to Puma

GitLabBlog13 Sept

Why we created a Memory team at GitLab

GitHubBlog4 Jun

Direct instruction marking in Ruby 2.6

SlackBlog3 Mar

Reducing Slack’s memory footprint

MetaBlog27 Jun

Memory optimization for feeds on Android

MetaBlog16 Jun

Chat reaches 1 billion messages sent per day