zhaocc1106

zhaocc1106's Stars

• vesoft-inc/nebula

  A distributed, fast open-source graph database featuring horizontal scalability and high availability

  Language:C++11k1.2k

• xtensor-stack/xtensor

  C++ tensors with broadcasting and lazy computing

  Language:C++3.4k402

• ztxz16/fastllm

  纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

  Language:C++3.4k348

• GitHubDaily/GitHubDaily

  坚持分享 GitHub 上高质量、有趣实用的开源技术教程、开发者工具、编程网站、技术资讯。A list cool, interesting projects of GitHub.

  33.5k3.6k

• ruanyf/weekly

  科技爱好者周刊，每周五发布

  51k3.1k

• luhengshiwo/LLMForEverybody

  每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

  Language:Jupyter Notebook52732

• facebookresearch/generative-recommenders

  Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

  Language:Python837154

• NetEase-Media/ControlTalk

  Official code for "Controllable Talking Face Generation by Implicit Facial Keypoints Editing"

  Language:Python191

• zurutech/pillow-resize

  Porting of Pillow resize method in C++ and OpenCV.

  Language:C++12816

• NVIDIA/CUDALibrarySamples

  CUDA Library Samples

  Language:Cuda1.7k355

• THUDM/GLM-4-Voice

  GLM-4-Voice | 端到端中英语音对话模型

  Language:Python2.5k202

• OpenGVLab/InternVL

  [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

  Language:Python6.7k521

• NetEase-Media/grps_trtllm

  【高性能OpenAI LLM服务】通过GPRS+TensorRT-LLM+Tokenizers.cpp实现纯C++版高性能OpenAI LLM服务，支持chat和function call模式，支持ai agent，支持分布式多卡推理，支持多模态，支持gradio聊天界面。

  Language:C++1003

• run-llama/llama_index

  LlamaIndex is a data framework for your LLM applications

  Language:Python37.8k5.4k

• kyutai-labs/moshi

  Language:Python7.1k552

• QwenLM/Qwen2-VL

  Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

  Language:Python4.1k248

• BBuf/how-to-optim-algorithm-in-cuda

  how to optimize some algorithm in cuda.

  Language:Cuda1.8k150

• NetEase-Media/grps_vllm

  【grps接入vllm】通过vllm LLMEngine Api实现LLM服务。

  Language:Python7

• alibaba/PhotonLibOS

  Probably the fastest coroutine lib in the world!

  Language:C++927128

• zhaohb/fastapi_tritonserver

  Language:Python276

• jinja2cpp/Jinja2Cpp

  Jinja2 C++ (and for C++) almost full-conformance template engine implementation

  Language:C++51187

• buptzyb/tensorflow

  An Open Source Machine Learning Framework for Everyone

  Language:C++43

• NVIDIA/TensorRT-Model-Optimizer

  TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.

  Language:Python65347

• gpu-mode/lectures

  Material for gpu-mode lectures

  Language:Jupyter Notebook3.4k344

• xuchengsheng/spring-reading

  涵盖了 Spring 框架的核心概念和关键功能，包括控制反转（IOC）容器的使用，面向切面编程（AOP）的原理与实践，事务管理的方式与实现，Spring MVC 的流程与控制器工作机制，以及 Spring 中数据访问、安全、Boot 自动配置等方面的深入研究。此外，它还包含了 Spring 事件机制的应用、高级主题如缓存抽象和响应式编程，以及对 Spring 源码的编程风格与设计模式的深入探讨。

  Language:Java8.9k1.1k

• NetEase-Media/grps

  【深度学习模型部署框架】支持tf/torch/trt/trtllm/vllm以及更多nn框架，支持dynamic batching、streaming模式，支持python/c++双语言，可限制，可拓展，高性能。帮助用户快速地将模型部署到线上，并通过http/rpc接口方式提供服务。

  Language:C++17013

• netease-youdao/QAnything

  Question and Answer based on Anything.

  Language:Python12.2k1.2k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python14.9k1.4k

• mysql/mysql-connector-cpp

  MySQL Connector/C++ is a MySQL database connector for C++. It lets you develop C++ and C applications that connect to MySQL Server.

  Language:C++639247

• bombela/backward-cpp

  A beautiful stack trace pretty printer for C++

  Language:C++3.9k485