LLM & Inference

irresponsible innovation. Try now at https://chat.dev/

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

A throughput-oriented high-performance serving framework for LLMs

This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.

A highly optimized LLM inference acceleration engine for Llama and its variants.

Magick is a cutting-edge toolkit for a new kind of AI builder. Make Magick with us!

The most easy-to-understand tutorial for using LoRA (Low-Rank Adaptation) within diffusers framework for AI Generation Researchers🔥

Llama 3+ inference in pure Java

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models

FireAct: Toward Language Agent Fine-tuning

LLMFlows - Simple, Explicit and Transparent LLM Apps

Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

The official implementation of Self-Play Preference Optimization (SPPO)

CLI for running large numbers of coding agents in parallel with git worktrees

LLM (Large Language Model) FineTuning

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

A low-latency & high-throughput serving engine for LLMs

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

🔥🔥🔥[AAAI 2026 Oral] Official Implementation of Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

A command-line interface tool for serving LLM using vLLM.

Self-hosted personalized AI in a mirror.

Efficient AI Inference & Serving

LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)

不想啃 5000+ 全文？我已经替你和 LLM 啃完了 — ICLR 2026 全景中文导读

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)

Odyssey: Empowering Minecraft Agents with Open-World Skills

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

活字通用大模型

Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.

HiveMind Protocol - A Local-First, Privacy-Preserving Architecture for Agentic RAG

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Production-ready data processing made easy and shareable

AutoAudit—— the LLM for Cyber Security 网络安全大语言模型

Qwen3 Fine-tuning: Medical R1 Style Chat

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning

One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.

SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression

Method for Long Context RLMs using verifiable Lambda Calculus

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papers on accelerating LLMs, currently focusing mainly on inference acceleration, and related works will be gradually added in the future. Welcome contributions!

[ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀

CUDA编程练习项目-Hands-on CUDA kernels and performance optimization, covering GEMM, FlashAttention, Tensor Cores, CUTLASS, quantization, KV cache, NCCL, and profiling.