NetEase-Media / grps
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.
☆157Updated last week
Alternatives and similar repositories for grps:
Users that are interested in grps are comparing it to the libraries listed below
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆125Updated last week
- TengineGst is a streaming media analytics framework, based on GStreamer multimedia framework, for creating varied complex media analytics…☆57Updated 3 years ago
- 用VLLM框架部署千问1.5并进行流式输出☆91Updated 11 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆219Updated 6 months ago
- Algorithm acceleration landing framework, let you complete the development of algorithm at low cost.eg: Facedetect, FaceLandmark..☆68Updated 3 years ago
- 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力☆147Updated 8 months ago
- 🚀 Do not need libtorch, pure C++ TensorRT deploys SOLOv2 etc, which can be quickly ported to NX/TX2.☆43Updated 2 years ago
- Support mixed-precsion inference with vllm☆80Updated 2 months ago
- Mixed precision inference by Tensorrt-LLM☆78Updated 5 months ago
- 模型部署白皮书(CUDA|ONNX|TensorRT|C++)🚀🚀🚀☆190Updated 6 months ago
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆83Updated 5 months ago
- 教你只用最基本的python语法和numpy一步步实现深度学习框架☆127Updated 8 months ago
- Ai edge toolbox，专门面向边端设备尤其是嵌入式RTOS平台，AI模型部署工具链，包括模型推理引擎和模型压缩工具☆151Updated last year
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated last year
- 基于200万条医疗数据对DeepSeek-R1-Distill-Qwen-32B进行fine tune且部署☆138Updated last month
- An ultra fast tiny model for lane detection, using onnx_parser, TensorRTAPI, torch2trt to accelerate. our model support for int8, dynamic…☆120Updated 3 years ago
- SegmentAnything-OnnxRunner is an example using Meta AI Research's SAM onnx model in C++.The encoder and decoder of SAM are decoupled in t…☆94Updated last year
- JittorGeometric is a Jittor-based graph machine learning library.☆154Updated last week
- Hands-on construction of a complete neural network☆14Updated last year
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆881Updated last week
- Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms…☆446Updated 7 months ago
- An open source task scheduling library ASRT (Async Runtime) written in modern C++ tailored for embedded linux systems.☆99Updated last month
- 保险行业回访外呼机器人☆62Updated 2 years ago
- Chinese large language model☆117Updated last year
- DeepRetrieval - Hacking 🔥Real Search Engines and Text/Data Retrievers with LLM + RL☆201Updated this week
- Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.☆65Updated 8 months ago
- ☆39Updated this week
- Build CUDA Neural Network From Scratch☆16Updated 7 months ago
- 从预训练到强化学习的中文llama2☆88Updated last year
- Code and data for crosstalk text generation tasks, exploring whether large models and pre-trained language models can understand humor. …☆144Updated 2 years ago