AI Chip Architectures
A look at AI Chip Architectures. NVIDIA, AMD, TPUs, Trainium, Groq, Cerebras.
Topic
#system-design
25 篇笔记
SemiAnalysis 发布 AgentX InferenceXv3 研报，Mooncake 成为关键基础设施
SemiAnalysis 发布 AgentX InferenceXv3，用大规模真实 Agentic workload 重新审视推理系统性能。随着长上下文、多轮交互和 KV Cache 复用成为常态，Agentic Inference 正从“拼算力”走向系统级优化，而 Mooncake 也正在其中扮演越来越重要的基础设施角色。
The Audit Log Page
An audit log has two readers. Most logs are designed for the wrong one. Five theses on product audit logs.
Consistent Hashing is kinda cool
Hii in this blog I will try to cover consistent hashing in detail from top to bottom. But before getting into consistent hashing, let’s firs...
Building the last WAL on S3
Nearly two years ago, we started Archil with a simple realization: it was clear that people were spending immense effort to build new, serve...
wal3: A Write-Ahead Log for Chroma, Build on Object Storage
wal3, Chroma's write-ahead log, combining a 30-year-old lock-free algorithm with S3's newest conditional writes feature.
Formally verified distributed locks for sandboxes
I’m wrapping up my internship at Modal, where I worked on our new, massively scalable sandbox architecture.
Git at any scale
Cursor is the best AI coding agent., Git at any scale
所有想做 FDE 的人，都该读懂 Palantir 这套方法
大模型进入企业以后，最难的一步是把一家公司的数据、规则和权力关系，变成 AI 能够理解并安全执行的系统。2026 年 5 月，OpenAI 成立了一家专门负责企业部署的新公司。它准备投入超过 40 亿美元，并计划通过收购 Tomoro，一次带入约 150 名 Forward De...
Concurrency vs. Throughput: why more parallelism can make databases slower
Increasing throughput sometimes requires reducing parallelism. A look into why this is the case for Vitess + MySQL databases
YC 开源 QM：当每个员工都有 Agent，公司需要怎样的协作系统？
未来一家公司里，可能每个员工都有自己的 Agent。它们能读文件、查数据库、写代码、回复邮件，也能在后台持续运行任务。问题随之而来：这些 Agent 应该看到什么？记住什么？使用谁的账号？哪些能力可以共享？危险动作由谁批准？7 月 31 日，Y Combinator 开源的 QM...
Agency: Secure, scalable sandboxes for agents
This is part of our series on how we're AI-pilling Sierra.In our last few posts, we talked about what happens when every employee has a sing...
We rewrote our agent to run entirely in a Durable Object with Pi, Agents SDK and Code Mode
We recently finished moving the camelAI agent off of virtual machines. The agent now runs inside a Cloudflare Durable Object, its filesystem...
Designing a programmable runtime for agent orchestration
This article introduces Onyx, our VM for programmable agent orchestration. And by extension, a runtime that turns orchestration into softwar...
15 AI Agent Design Patterns Every Engineer Must Know
Every team building AI agents hits the same wall.You start with one prompt and a few tools.It works. Then requirements grow. More edge cases...
Migrating LiteLLM to Rust - Building the Fastest and Litest AI Gateway
LiteLLM is moving its AI gateway to Rust: 15x throughput, 11x less memory, and sub-1ms per-request overhead. No v2, no migration, your config stays the same.
The 7 Types of Agent Memory: A Technical Guide for AI Engineers
Agent memory explained: the 7 types — working, semantic, episodic, procedural, retrieval, parametric, prospective — and when to build each.
Complete Map of Graph Technology 2026: 128 Products, 7 Categories
The complete guide to graph databases, knowledge graphs, GraphAI, and more. 7 categories, 128 graph technology products, 113 vendors
Building Reliable Agentic AI Systems
AI helping pharmaceutical researchers query decades of information buried in PDF reports
Launching a million sandboxes per second in constant time
They say that in the future, everyone will have their own sandbox company for 15 minutes. Let's make that simpler, here's exactly how I buil...
Building cloud agent infrastructure: what's different, and what we learned
Most agent frameworks today assume a desktop. One user, one machine, one process. The agent runs while the laptop is open, writes to a local...
When AI builds itself
Our progress toward recursive self-improvement, and its implications.
protocols for transactional usage of object storage
building correct applications w/o external coordination
Inside vLLM: Anatomy of a High-Throughput LLM Inference System
From paged attention, continuous batching, prefix caching, specdec, etc. to multi-GPU, multi-node dynamic serving at scale.
Building and operating a pretty big storage system called S3
Three distinct perspectives on scale that come along with building and operating a storage system the size of S3.