Rui Ren's repositories
builder
Continuous builder and binary build scripts for pytorch
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
mlops-v2
Azure MLOps (v2) solution accelerators.
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnxruntime-genai
Generative AI extensions for onnxruntime
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
azure-docs
Open source documentation of Microsoft Azure
build-onnx-ort-torch-from-source
build onnx onnxruntime and pytorch from souce
chatgpt_academic
科研工作专用ChatGPT拓展，特别优化学术Paper润色体验，支持自定义快捷按钮，支持markdown表格显示，Tex公式双显示，代码显示功能完善，新增本地Python工程剖析功能/自我剖析功能
DeepSpeedExamples
Example models using DeepSpeed
dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
dolly-benchmark
Dolly benchmark test and optimization
Eval
LLM Evaluation and Perf
evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Fabmedical
Kubernates Orchestration
generative-ai-for-beginners
18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
LLM-online-inference
LLM online inference benchmark
Multimodal-Inference
backup of vision model demo scrips
neurips_llm_efficiency_challenge
NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day
optimum
🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools
optimum-benchmark
A unified multi-backend utility for benchmarking Transformers and Diffusers with full support of Optimum's hardware optimizations & quantization schemes.
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
pytorch.github.io
The website for PyTorch
swift
ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs
text-generation-inference
Large Language Model Text Generation Inference
vim
vim configurations
whisper.cpp
Port of OpenAI's Whisper model in C/C++