#
Starred repositories
[Support 0.49.x]（Reset Cursor AI MachineID & Bypass Higher Token Limit） Cursor Ai ，自动重置机器ID ， 免费升级使用Pro功能: You've reached your trial request limit. / Too many free trial accounts used on this machi…
A framework that support executing unmodified CUDA source code on non-NVIDIA devices.
A Datacenter Scale Distributed Inference Serving Framework
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
No fortress, purely open ground. OpenManus is Coming.
Small tool to disable macOS 15's annoying new screencapture nag popups
Machine learning compiler based on MLIR for Sophgo TPU.
✨ Programming Language Research, Applied PLT & Compilers
MoBA: Mixture of Block Attention for Long-Context LLMs
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Machine Learning Engineering Open Book
Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
Fast and memory-efficient exact attention
FlashMLA: Efficient MLA decoding kernels
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
Development repository for the Triton language and compiler
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
A framework for few-shot evaluation of language models.
A Python Project Template for Long-Term Maintainability
Explore LLM model deployment based on AXera's AI chips
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）