Stars
This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov
SGLang is a fast serving framework for large language models and vision language models.
PruningRadixTrie - 1000x faster Radix trie for prefix search & auto-complete
A from-scratch experimental AOT JS engine, written in JS
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Fully open reproduction of DeepSeek-R1
streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL
An idiomatic and fast QP-trie implementation in pure Rust.
Represent large sets and maps compactly with finite state transducers.
Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world
Drogon: A C++14/17/20 based HTTP web application framework running on Linux/macOS/Unix/Windows
A Bulletproof Way to Generate Structured JSON from Language Models
Rapid fuzzy string matching in Python using various string metrics
Rapid fuzzy string matching in Rust using various string metrics
SIMD-accelerated library for computing global and X-drop affine gap penalty sequence-to-sequence or sequence-to-profile alignments using an adaptive block-based algorithm.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
Minimalistic 4D-parallelism distributed training framework for education purpose
Python tool for converting files and office documents to Markdown.
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
Code repo for the paper "SpinQuant LLM quantization with learned rotations"
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
Everything about the SmolLM2 and SmolVLM family of models