llama3 implementation one matrix multiplication at a time

A high-throughput and memory-efficient inference and serving engine for LLMs

A multi-level tensor algebra superoptimizer

MLX: An array framework for Apple silicon

A library for building fast, reliable and evolvable network services.

A user-friendly CMS for static site generators.

A container runtime written in Rust

A static site generator for data apps, dashboards, reports, and more. Observable Framework combines JavaScript on the front-end for interactive graphics with any language on the back-end for data a…

FlashInfer: Kernel Library for LLM Serving

Building a quick conversation-based search demo with Lepton AI.

a unified scheduler for online and offline tasks

Build better UIs faster.

A SolidJS diagramming framework

simple markdown editor w inline comments, on latest automerge stack

Ensō is a high-performance streaming interface for NIC-application communication.

Kepler (Kubernetes-based Efficient Power Level Exporter) uses eBPF to probe performance counters and other system stats, use ML models to estimate workload energy consumption based on these stats, …

a Rust library for parsing, validating, and modifying Dockerfiles

Docker image identifier parser.

Module, Model, and Tensor Serialization/Deserialization

SQL databases in Python, designed for simplicity, compatibility, and robustness.

Large Language Model Text Generation Inference

LLM papers I'm reading, mostly on inference and model compression

A fast, clean, responsive Hugo theme.

A monitor of resources

A lightweight quadtree implementation for javascript

S3 Service Adapter

Rust crates to extend containerd

得意黑 Smiley Sans：一款在人文观感和几何特征中寻找平衡的中文黑体

🔥 Blazing fast bulk data transfers between any cloud 🔥

Standalone Kubelet Tutorial