AutoMQ is a cloud-native alternative to Kafka by decoupling durability to cloud storage services like S3. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency…

Port of Facebook's LLaMA model in C/C++

LLM inference in C/C++

📚FFPA(Split-D): Yet another Faster Flash Attention with O(1) GPU SRAM complexity large headdim, 1.8x~3x↑🎉 faster than SDPA EA.

📚Modern CUDA Learn Notes: 200+ Tensor/CUDA Cores Kernels🎉, HGEMM, FA2 via MMA and CuTe, 98~100% TFLOPS of cuBLAS/FA2.

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

The cross-platform open-source app built for handwriting

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

A free and open source, self hosted Ai based live meeting note taker and minutes summary generator that can completely run in your Local device (Mac OS and windows OS Support added. Working on addi…

10 Lessons to Get Started Building AI Agents

A Python native, OS native GUI toolkit.

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO & designed for fine-tuning.

This project aims to achieve good results in handwritten mathematical formulas, printed formulas, complex formula samples, or comprehensive optical character recognition tasks.

Modular hardware build system

Masked Generative Distillation (ECCV 2022)

NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills.

verl: Volcano Engine Reinforcement Learning for LLMs

The macOS & iOS file archiver

Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Highlight).

一键安装程序，欢迎大家提交代码和小鱼一起一键安装停止浪费生命

Janus-Series: Unified Multimodal Understanding and Generation Models

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient MLA decoding kernels

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen2.5, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3…

A Python-embedded modeling language for convex optimization problems.

A cross-platform video structuring (video analysis) framework. If you find it helpful, please give it a star: ) 跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星 : )

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding