Ray Serve: Advancing Flexibility with Async Inference, Custom Request Routing, and Custom Autoscaling

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.

pw_async2: Informed poll — Pigweed

pw_async2: Cooperative async tasks for embedded

Can JavaScript Become a Planned Runtime? — A study of AOT compilation, computation graphs, memory planning, and concurrency scheduling

An In-Depth Overview of the Apache Iceberg 1.11.0 Release

Designing a faster data model to personalize browsing in real time

Optimizing API endpoint performance for browsing personalisation.

Multi-Tool Orchestration with RAG approach using OpenAI's Responses API

Cookbook to route queries across tools with RAG using the Responses API.

Multi-Tool Orchestration with RAG approach using OpenAI's Responses API

Cookbook to route queries across tools with RAG using the Responses API.