Repositories list

• grps_trtllm

  Public
  Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

  openaimulti-modalphi+ 17function-callqwqai-agentllmllama-indexchatglminternvideo+ 10

  Python

  •

  Apache License 2.0

  •11•139•7•0•Updated May 14, 2025May 14, 2025

• grps

  Public
  Deep Learning Deployment Framework: Supports tf/torch/trt/trtllm/vllm and other NN frameworks. Support dynamic batching, and streaming modes. It is dual-language compatible with Python and C++, offering scalability, extensibility, and high performance. It helps users quickly deploy models and provide services through HTTP/RPC interfaces.

  tensorflowtorchtensorrt+ 5servingtriton-inference-serverdynamic-batchingvllmtensorrt-llm

  C++

  •

  Apache License 2.0

  •13•164•0•0•Updated May 8, 2025May 8, 2025

• TensorRT-LLM

  Public
  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.

  C++

  •

  Apache License 2.0

  •1.5k•0•0•0•Updated May 8, 2025May 8, 2025

• HSTU-Tensorflow

  Public
  Python

  •

  MIT License

  •2•2•0•0•Updated Mar 20, 2025Mar 20, 2025

• HGCDR

  Public
  Official code for "Heterogeneous Graph-based Framework with Disentangled Representations Learning for Multi-target Cross Domain Recommendation"

  Python

  •

  MIT License

  •0•1•0•0•Updated Nov 21, 2024Nov 21, 2024

• FPARec

  Public
  Official code for "Learning Positional Attention for Sequential Recommendation"

  Python

  •0•2•0•0•Updated Nov 15, 2024Nov 15, 2024

• ControlTalk

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

  Python

  •

  MIT License

  •2•30•2•0•Updated Oct 31, 2024Oct 31, 2024

• grps_examples

  Public
  【grps服务样例】包含c++、python自定义工程以及快捷部署样例。

  C

  •

  Apache License 2.0

  •0•3•0•0•Updated Oct 28, 2024Oct 28, 2024

• grps_vllm

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

  vllm

  Python

  •

  Apache License 2.0

  •0•7•0•0•Updated Sep 3, 2024Sep 3, 2024

• nn-infer-opt

  Public
  网易新闻推荐模型推理优化相关

  C++

  •0•1•0•0•Updated Jul 2, 2024Jul 2, 2024

• easy-ngo

  Public
  easy-ngo是由网易传媒开发的基于Go语言的开发工具包，基于easy-ngo工具包，开发者可以快速构建高可用、大并发的应用。

  Go

  •

  Apache License 2.0

  •50•300•10•2•Updated Dec 29, 2023Dec 29, 2023

• easy-ngo-website

  Public
  JavaScript

  •

  Apache License 2.0

  •0•1•0•0•Updated Aug 14, 2023Aug 14, 2023

• easy-ngo-doc

  Public archive
  JavaScript

  •

  Apache License 2.0

  •3•3•0•0•Updated Aug 14, 2023Aug 14, 2023

• CSCE-Net

  Public
  Official code for "CSCE-Net: Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding"

  Python

  •

  MIT License

  •0•12•0•0•Updated Jun 1, 2023Jun 1, 2023

• easy-ngo-examples

  Public
  Go

  •

  Apache License 2.0

  •2•5•0•0•Updated Mar 24, 2023Mar 24, 2023

• easy-ngo-layout

  Public
  Apache License 2.0

  •0•0•0•0•Updated Feb 14, 2023Feb 14, 2023

• easy-ngo-tools

  Public
  Apache License 2.0

  •0•0•0•0•Updated Feb 10, 2023Feb 10, 2023

• ngo

  Public archive
  Ngo是由网易传媒基础技术团队开源的一个类似Java Spring Boot的框架，全部使用Go语言开发，做到快速开发应用

  Go

  •

  Apache License 2.0

  •36•187•29•1•Updated Feb 9, 2023Feb 9, 2023

• ngo-demo

  Public archive
  ngo-demo示例

  Go

  •2•0•0•0•Updated Feb 9, 2023Feb 9, 2023

• netease-media.github.io

  Public
  0•0•0•0•Updated Feb 9, 2023Feb 9, 2023

• PAMM-HiA-T5

  Public
  codes for PAMM-HiA-T5 method

  Python

  •

  MIT License

  •0•3•1•0•Updated Feb 2, 2023Feb 2, 2023