Lists (8)
Stars
A blazingly fast, minimalist HTTP server built for modern Rust applications.
slatedb / fail-parallel
Forked from tikv/fail-rsA fork of TiKV's fail-rs that supports parallel execution.
a fork of html-to-markdown with speed enhancements
Harbor is a framework for running agent evaluations and creating and using RL environments.
Karpathy's LLM-Wiki vision, fully realized — wiki-centric full-lifecycle AI research platform powered by Claude Code
Open-source streaming SQL engine written in Rust using Apache Arrow and DataFusion. Supports continuous queries, temporal stream joins, tumbling/session windows, and CDC/Kafka connectors. Lightweig…
An open, sub-millisecond, single-executable Firebase alternative with type-safe APIs, built-in WebAssembly runtime, realtime subscriptions, auth, and admin UI built on Rust, SQLite & Wasmtime.
A memory efficient string type that can store up to 24* bytes on the stack
Speaker diarization in Rust. 312–912x realtime on Apple Silicon, 50–121x on CUDA. Matches pyannote accuracy.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Slint backend for jailbroken Kindles. Create rich GUI apps with Rust!
A local workbench for agents doing continuous work across sessions, commands, human input, and external events.
Fastest pure Rust implementation of LZ4 compression/decompression.
MEA provides async primitives and combinators that are runtime agnostic.
Fast, streaming indexing, query, and agentic LLM applications in Rust
Distributed timestamp & sequence oracle for Rust — strictly monotonic timestamps and gapless, dense ID sequences over gRPC, replicated with pluggable consensus.
Zero-copy, content-addressed Rust build cache. No copies, no wasted disk — just hardlinks locally and S3 for sharing.
Modern embedded framework, using Rust and async.
QuantMind 开源版 是一款面向个人量化研究者的本地化金融量化交易平台，基于微软 Qlib 量化框架构建，提供从模型训练，回测，推理，实盘交易的完整研究闭环。 平台深度集成 LightGBM 等主流机器学习模型，支持 146 维量化因子训练与推理，用户可快速构建 Alpha 策略并在历史数据上验证效果。核心功能涵盖智能策略生成、模型训练、回测中心、QuantBot 助手及多模型管理，全…
Your Personal AI super intelligence. Private, Simple and extremely powerful.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.