Lists (1)
Stars
slime is an LLM post-training framework for RL Scaling.
A multi-agent orchestration skill for unattended, long-running engineering tasks.
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…
JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A community collection of OpenClaw use cases for making life easier.
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
SGLang is a high-performance serving framework for large language models and multimodal models.
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Qianfan-VL: Domain-Enhanced Universal Vision-Language Models
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
A simple, fast and user-friendly alternative to 'find'
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
Open-source and strong foundation image recognition models.
Demo of a customer service use case implemented with the OpenAI Agents SDK
A lightweight LMM-based Document Parsing Model
"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion" code repository
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
chDB is an in-process OLAP SQL Engine 🚀 powered by ClickHouse
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool