Stars
Enforce the output format (JSON Schema, Regex etc) of a language model
Derivative-based regular expression engine for Rust
Edit Banana: A framework for converting statistical figures into editable formats.
FlashInfer: Kernel Library for LLM Serving
Block Diffusion for Ultra-Fast Speculative Decoding
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
A GUI to quickly manage your WSL2 instances
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
A python module to repair invalid JSON from LLMs
HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
Cost-efficient and pluggable Infrastructure components for GenAI inference
Achieve state of the art inference performance with modern accelerators on Kubernetes
A character-level language diffusion model trained on Tiny Shakespeare
A research project exploring fine-tuning BERT-style models for text generation
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Bash Line Editor―a line editor written in pure Bash with syntax highlighting, auto suggestions, vim modes, etc. for Bash interactive sessions.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
Bash script for installing V2Ray in operating systems such as Debian / CentOS / Fedora / openSUSE that support systemd