Yet another minimalist deep-learning framework optimized for inference

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

PyTorch bindings for CUTLASS grouped GEMM.

fused MoE kernel in Candle backend

NVTX API support for Rust

A fixed-size circular buffer written in Rust.

CLI utility to inspect and explore .safetensors and .gguf files

A SPA built with React and TypeScript, using Hono for serverless functionality and deployed on Cloudflare Pages.

Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and WordPiece tokenization in JavaScript, Python and Rust.

Core building blocks for AI apps. High-quality, accessible, and customizable components for AI interfaces.

Rust tooling to use Wasm Components over HTTP

Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Community Support: https://discord.com/invite/stackblitz

A multiprocess drop-in replacement for Rust channels

Experimental compiler for deep learning models

Minimalist ML framework for Rust

A Rust crate offering similar functionality to the Python transformers package using Candle.

A type-safe, K-sortable, globally unique identifier

Fast, flexible LLM inference

AICI: Prompts as (Wasm) Programs

A SQLite extension for efficient vector search, based on Faiss!

Rust actor framework

This repo contains the markdown files and static assets powering developer.bigcommerce.com. https://developer.bigcommerce.com/

Rust implementation of the HNSW algorithm (Malkov-Yashunin)

Build script crate to run npm commands.

Rust port of sentence-transformers (https://github.com/UKPLab/sentence-transformers)

A library for writing reactive single page web apps

PHP gRPC Framework

The Grafbase GraphQL Federation Gateway