Lists (2)
Stars
CMake toolchain for Nintendo Switch homebrew development
DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
[DAC2024] A Holistic Functionalization Approach to Optimizing Imperative Tensor Programs in Deep Learning
An intuitive and low-overhead instrumentation tool for Python
A Next-Generation Training Engine Built for Ultra-Large MoE Models
A PyTorch native platform for training generative AI models
Analyze computation-communication overlap in V3/R1.
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
DeepEP: an efficient expert-parallel communication library
A debugging and profiling tool that can trace and visualize python code execution
Easiest and laziest way for building multi-agent LLMs applications.
A high-throughput and memory-efficient inference and serving engine for LLMs
第三方B站客户端，目前可以运行在PC全平台、PSVita、PS4 、Xbox 和 Nintendo Switch上
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Access private members and statics of a C++ class
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
workspace是基于C++11的轻量级异步执行框架，支持：通用任务异步并发执行、优先级任务调度、自适应动态线程池、高效静态线程池、异常处理机制等。
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
An open-source tool-augmented conversational language model from Fudan University
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.